© 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. 45742
    Prev
    Next
    INDEX
    Explanations

    Fukushima

    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
     gainera
    -0.54
    unanje
    -0.52
     scolaires
    -0.52
    lilla
    -0.48
    onomy
    -0.46
    Попис
    -0.46
     bersih
    -0.46
    ienka
    -0.44
    ayage
    -0.44
    Remix
    -0.43
    POSITIVE LOGITS
    出版年
    0.74
     protoimpl
    0.72
    SourceChecksum
    0.68
    findpost
    0.66
    writeFieldEnd
    0.66
    RTLR
    0.62
    //};
    0.62
     jPanel
    0.60
    __'
    0.60
    styleType
    0.59
    Activations Density 0.021%

    No Known Activations