© 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. 9909
    Prev
    Next
    INDEX
    Explanations

    references to players and their performance statistics in sports contexts

    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
    Negative Logits
    Geplaatst
    -0.63
    曖昧さ回避
    -0.59
     vermelhas
    -0.59
    بوابة
    -0.57
    -------------</
    -0.56
    endmodule
    -0.56
     navideños
    -0.55
    DoubleQuotes
    -0.54
     chão
    -0.54
     désolés
    -0.52
    POSITIVE LOGITS
    ukone
    0.59
    SizeF
    0.52
    cheiben
    0.51
    himovic
    0.51
    ProgressHUD
    0.48
     Reverso
    0.47
    maiden
    0.47
    ambu
    0.47
    าสตร์
    0.46
    lichung
    0.45
    Activations Density 0.060%

    No Known Activations