© 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. 91168
    Prev
    Next
    INDEX
    Explanations

    veal

    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
    alian
    -1.87
    veal
    -1.16
    ALIAN
    -0.96
    ContextHolder
    -0.56
    alians
    -0.54
     تضيفلها
    -0.52
     otomatig
    -0.52
     الرياضيه
    -0.51
    TintMode
    -0.50
    rapie
    -0.50
    POSITIVE LOGITS
    numerusform
    0.56
    fjspx
    0.56
     setuptools
    0.55
    DIRECTIONS
    0.54
    udessa
    0.54
    divarius
    0.52
     Loyal
    0.51
     fla
    0.50
    INCREF
    0.50
    enumerate
    0.50
    Activations Density 0.089%

    No Known Activations