© 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. 20925
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, specifically those involving bleeding and related procedures

    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
    SerializedSize
    -0.66
    GraphicsUnit
    -0.63
    گاه
    -0.56
    Bibliograf
    -0.56
    odotus
    -0.51
     Etter
    -0.51
    ovács
    -0.51
    fjspx
    -0.51
     Bouquet
    -0.49
    abbr
    -0.49
    POSITIVE LOGITS
    @[+][
    0.70
    writeFieldEnd
    0.62
    `;
    0.56
    DeleteBehavior
    0.55
    MigrationBuilder
    0.54
     esternos
    0.53
    ;*/
    0.52
    </tfoot>
    0.51
    numerusform
    0.51
    ")));
    0.51
    Activations Density 0.450%

    No Known Activations