© 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. 4-CLT-HP
    7. 3488
    Prev
    Next
    INDEX
    Explanations

    s

    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
    AddTagHelper
    -0.82
    出版年
    -0.67
    Autoritní
    -0.60
    (")");
    -0.60
     بيها
    -0.58
     AssemblyCulture
    -0.57
     portanto
    -0.56
    bitField
    -0.56
     متعلقه
    -0.54
    معلومات
    -0.54
    POSITIVE LOGITS
     Arkivert
    0.56
     important
    0.52
    สำคัญ
    0.49
     neuve
    0.49
     gogh
    0.48
    standig
    0.47
     hard
    0.47
     worth
    0.47
    wiście
    0.45
     native
    0.45
    Activations Density 0.003%

    No Known Activations