© 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. 15375
    Prev
    Next
    INDEX
    Explanations

    the closing parentheses in the text

    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
    then
    -0.50
    endregion
    -0.48
    ArgsConstructor
    -0.46
     livré
    -0.46
    бы
    -0.46
    Li
    -0.44
    Биография
    -0.43
    it
    -0.43
    ..
    -0.42
    tion
    -0.40
    POSITIVE LOGITS
    IsMutable
    0.89
    ValueStyle
    0.83
     Italijanski
    0.80
     >=",
    0.78
    aarrggbb
    0.77
    帖最后由
    0.77
    HtmlAttribute
    0.76
     tartalomajánló
    0.76
    AddTagHelper
    0.74
    MigrationBuilder
    0.74
    Activations Density 0.001%

    No Known Activations