© 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. 42296
    Prev
    Next
    INDEX
    Explanations

    sunlight

    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
     daylight
    -1.13
     myſelf
    -1.09
    ValueStyle
    -1.04
     itſelf
    -1.01
    DockStyle
    -0.95
     HttpNotFound
    -0.92
     HasFactory
    -0.91
     sunlight
    -0.91
     Sunlight
    -0.90
    daylight
    -0.89
    POSITIVE LOGITS
    /
    0.54
    g
    0.50
     to
    0.50
    .
    0.49
     /
    0.47
     (
    0.46
    ,
    0.46
    ComponentModel
    0.46
     or
    0.45
     k
    0.44
    Activations Density 0.044%

    No Known Activations