© 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. 44147
    Prev
    Next
    INDEX
    Explanations

    names or computer

    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
    ström
    -0.52
    ania
    -0.47
    ulemon
    -0.43
    strom
    -0.42
    ly
    -0.40
    i
    -0.38
    ur
    -0.37
    anthin
    -0.35
     halk
    -0.34
     storm
    -0.33
    POSITIVE LOGITS
    ValueStyle
    0.95
     незавершена
    0.81
     privilégi
    0.81
     فريبيس
    0.80
    httphttps
    0.73
    าสตร์
    0.73
    Referencie
    0.72
     للاسماء
    0.71
    PhysRevD
    0.71
    expliquer
    0.70
    Activations Density 1.299%

    No Known Activations