© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 290
    Prev
    Next
    INDEX
    Explanations

    medical research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Enlarged
    -0.95
    tillery
    -0.67
     estekak
    -0.60
    herself
    -0.56
    országban
    -0.55
     connexes
    -0.55
     resourceCulture
    -0.54
     незавершена
    -0.53
     StatefulWidget
    -0.53
    SequentialGroup
    -0.53
    POSITIVE LOGITS
    bitField
    0.53
    MENAFN
    0.52
    نان
    0.51
    addPreferredGap
    0.51
     CURIAM
    0.51
    mocha
    0.50
    ViewFeatures
    0.47
     graphql
    0.47
    ++];
    0.47
    новниш
    0.47
    Activations Density 0.008%

    No Known Activations