© 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. 91921
    Prev
    Next
    INDEX
    Explanations

    leading

    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
     leading
    -0.80
     Leading
    -0.67
    Leading
    -0.63
    leading
    -0.57
    Lead
    -0.51
     lead
    -0.50
     lontano
    -0.49
    ρός
    -0.49
     geldig
    -0.48
    -
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.79
     CURIAM
    0.70
    <bos>
    0.69
    piles
    0.64
    Rüyada
    0.63
    УДК
    0.63
    OGND
    0.63
    GTCX
    0.62
    cillor
    0.60
    PostExecute
    0.60
    Activations Density 0.123%

    No Known Activations