© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30387
    Prev
    Next
    INDEX
    Explanations

    terms related to ratings and evaluations

    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
     getRule
    -0.96
    berdayakan
    -0.81
    клопе
    -0.77
    __':
    -0.77
     ADF
    -0.77
    /**
    -0.77
    %;">
    -0.76
    verwijspagina
    -0.76
    `;
    -0.75
    ']?>
    -0.75
    POSITIVE LOGITS
     ratings
    1.28
     rating
    1.21
     Rating
    1.21
     Ratings
    1.21
    Rating
    1.00
    Ratings
    0.99
     RATING
    0.98
    rating
    0.96
    ratings
    0.96
     rated
    0.75
    Activations Density 0.004%

    No Known Activations