© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90990
    Prev
    Next
    INDEX
    Explanations

    Nuanced and controlled actions

    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
    Kanpo
    -0.82
     ISNI
    -0.77
     AssemblyCompany
    -0.72
     ویکی‌پدیای
    -0.70
     onOptions
    -0.70
     autorytatywna
    -0.69
    slidesPer
    -0.65
    ristmas
    -0.64
    出版年
    -0.64
    onActivityResult
    -0.64
    POSITIVE LOGITS
     pageContext
    0.62
    a
    0.57
    f
    0.50
    b
    0.48
    ern
    0.46
    u
    0.46
    o
    0.44
    λέον
    0.44
     overtime
    0.43
    r
    0.43
    Activations Density 0.370%

    No Known Activations