© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42302
    Prev
    Next
    INDEX
    Explanations

    cover

    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
     cover
    -1.38
    Cover
    -1.34
     COVER
    -1.34
     Cover
    -1.29
     Covering
    -1.29
     covered
    -1.23
     covering
    -1.23
     Covered
    -1.21
    cover
    -1.18
    COVER
    -1.16
    POSITIVE LOGITS
    AddTagHelper
    0.49
     `${
    0.47
     by
    0.46
     all
    0.46
    пло
    0.46
    ;->
    0.45
    by
    0.45
    UnifiedTopology
    0.44
     Ba
    0.44
    liptic
    0.43
    Activations Density 0.084%

    No Known Activations