© 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. 5-CLT-HP
    7. 96037
    Prev
    Next
    INDEX
    Explanations

    Academic writing

    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
    AndEndTag
    -0.90
    DoubleQuotes
    -0.88
     beginnetje
    -0.88
     ModelExpression
    -0.84
     Efq
    -0.83
     linkovi
    -0.82
    RenderAtEndOf
    -0.81
    MessageTagHelper
    -0.80
     وتسجيلات
    -0.79
     يتيمه
    -0.77
    POSITIVE LOGITS
     it
    0.84
     we
    0.62
     does
    0.56
     if
    0.54
    it
    0.54
     a
    0.54
     can
    0.52
     an
    0.49
     any
    0.48
     comes
    0.47
    Activations Density 0.000%

    No Known Activations