© 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. 10177
    Prev
    Next
    INDEX
    Explanations

    health

    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
     صوتيه
    -0.64
     متعلقه
    -0.61
    ThroughAttribute
    -0.60
    Искәрмәләр
    -0.59
    setVerticalGroup
    -0.58
    /**
    -0.58
     שוליים
    -0.56
    LabelTagHelper
    -0.56
    RenderAtEndOf
    -0.55
    cop
    -0.54
    POSITIVE LOGITS
     leksikon
    0.57
     NPY
    0.56
    Демографія
    0.50
     Romains
    0.49
    setupUi
    0.49
    GIVEREF
    0.48
     Opiniones
    0.48
     Negra
    0.47
    WriteLiteral
    0.47
    theless
    0.47
    Activations Density 0.014%

    No Known Activations