© 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. 91117
    Prev
    Next
    INDEX
    Explanations

    Unusual events

    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
     International
    -1.00
     civilization
    -0.98
    International
    -0.80
     INTERNATIONAL
    -0.74
     civilizations
    -0.74
     Int
    -0.73
    Int
    -0.71
     bust
    -0.63
     civilisation
    -0.62
     Intl
    -0.61
    POSITIVE LOGITS
    RenderAtEndOf
    1.09
     AssemblyVersion
    0.93
    Personensuche
    0.91
     препратки
    0.87
     незавершена
    0.85
    GeoNames
    0.82
    WebVitals
    0.81
    TargetException
    0.79
     defaultstate
    0.79
    RectangleBorder
    0.77
    Activations Density 0.620%

    No Known Activations