Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 69
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships, particularly in the context of implementation and effect

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.82
     Athenians
    -0.72
     Huguen
    -0.71
     Hadrian
    -0.70
     Mahomet
    -0.69
     Hopf
    -0.68
     Majefty
    -0.66
     Assyrian
    -0.65
     Phry
    -0.65
     Thebes
    -0.64
    POSITIVE LOGITS
     the
    1.58
     a
    1.10
     these
    1.05
    )";
    
    1.05
     their
    1.05
     our
    1.03
    .}(
    1.03
     both
    1.01
    "):
    
    1.00
     an
    0.96
    Activations Density 8.062%

    No Known Activations