© 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. 1-CLT-HP
    7. 9507
    Prev
    Next
    INDEX
    Explanations

    clay

    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
     clay
    -1.45
    clay
    -1.21
     Clay
    -1.20
     clays
    -1.19
    Clay
    -1.17
     CLAY
    -1.04
    CLAY
    -0.95
     arcilla
    -0.71
    setVerticalGroup
    -0.63
     clayey
    -0.63
    POSITIVE LOGITS
     שוליים
    0.68
    TypedDataSet
    0.65
    titleMargin
    0.65
    Попис
    0.63
    ſelf
    0.60
     unknownFields
    0.59
    bars
    0.59
    malink
    0.58
    pence
    0.57
    menistan
    0.57
    Activations Density 0.011%

    No Known Activations