© 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. 0-CLT-HP
    7. 97697
    Prev
    Next
    INDEX
    Explanations

    file editing

    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
     ome
    -0.88
    edited
    -0.82
     Lorenz
    -0.80
    脚注の使い方
    -0.73
    writeField
    -0.67
    ClientSize
    -0.63
     мәкал
    -0.62
    原始内容存档于
    -0.60
    Izvori
    -0.60
    olfen
    -0.59
    POSITIVE LOGITS
    HEL
    0.52
    upa
    0.48
    tesy
    0.48
    mrow
    0.45
    the
    0.44
    gle
    0.44
    pat
    0.44
    GLE
    0.44
     braccia
    0.43
    you
    0.43
    Activations Density 0.080%

    No Known Activations