© 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. 28630
    Prev
    Next
    INDEX
    Explanations

    references to committees and advisory boards

    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
    AnimationsModule
    -0.73
    Datuak
    -0.69
    ########.
    -0.64
    новниш
    -0.62
    HostException
    -0.60
    bürgermeister
    -0.59
    corpion
    -0.59
     <<=
    -0.58
    Obrázky
    -0.56
    ViewImports
    -0.56
    POSITIVE LOGITS
     committee
    0.61
     subcommittee
    0.60
     committees
    0.59
     panel
    0.58
     Committee
    0.50
     panelists
    0.50
     Subcommittee
    0.49
     synch
    0.49
     jSON
    0.49
    usschuss
    0.49
    Activations Density 0.074%

    No Known Activations