© 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. 5-CLT-HP
    7. 96057
    Prev
    Next
    INDEX
    Explanations

    are

    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
    <bos>
    -1.19
    Autoritní
    -0.66
     autorytatywna
    -0.51
    новниш
    -0.46
    ibatis
    -0.45
    러나
    -0.45
    гъл
    -0.43
    لينكات
    -0.43
     sho
    -0.42
     noDo
    -0.42
    POSITIVE LOGITS
     onlyOwner
    0.61
    __(/*!
    0.57
     vela
    0.56
     Alamofire
    0.55
    HeaderText
    0.54
     Escolar
    0.53
    chymal
    0.53
     mijne
    0.52
     lada
    0.50
    bitField
    0.50
    Activations Density 0.084%

    No Known Activations