© 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. 20-CLT-HP
    4. 74633
    Prev
    Next
    INDEX
    Explanations

    Computer-generated texts

    np_max-act-logits · 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
     increase
    -0.66
    Increase
    -0.62
    increase
    -0.62
     Increase
    -0.61
     save
    -0.61
     réduction
    -0.60
     Save
    -0.56
    Save
    -0.54
     reduction
    -0.53
    reduction
    -0.53
    POSITIVE LOGITS
    +#+#
    0.71
    ReusableCell
    0.69
     ModelExpression
    0.69
    σθαι
    0.69
    DoubleQuotes
    0.68
     BoxDecoration
    0.66
    __(/*!
    0.62
     useAuth
    0.61
    évaluateur
    0.60
    aryen
    0.59
    Activations Density 0.001%

    No Known Activations