© 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. 94016
    Prev
    Next
    INDEX
    Explanations

    value/quality

    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
    RenderAtEndOf
    -1.55
    ConstraintMaker
    -1.52
     importance
    -1.51
    importance
    -1.49
    contentLoaded
    -1.45
    MigrationBuilder
    -1.38
     виправивши
    -1.33
    ImageContext
    -1.33
    OGND
    -1.32
     Importance
    -1.29
    POSITIVE LOGITS
     of
    1.05
     in
    0.72
    .
    0.62
     a
    0.61
     for
    0.59
     on
    0.56
    of
    0.55
     an
    0.54
     the
    0.53
    es
    0.52
    Activations Density 0.287%

    No Known Activations