© 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. 25052
    Prev
    Next
    INDEX
    Explanations

    specific sequences of digits or numbers

    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
    IndentedString
    -1.30
    MigrationBuilder
    -1.03
     שוליים
    -0.95
    참고
    -0.94
    #+#
    -0.90
     يتيمه
    -0.87
    principalTable
    -0.87
    ()?;
    -0.87
    WillAppear
    -0.86
     Réponses
    -0.85
    POSITIVE LOGITS
     Partagez
    0.44
    os
    0.42
     in
    0.41
    InputBorder
    0.40
    ток
    0.39
    クロ
    0.37
    (
    0.37
    is
    0.37
     oog
    0.37
    机
    0.37
    Activations Density 0.004%

    No Known Activations