© 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. 15671
    Prev
    Next
    INDEX
    Explanations

    trigonometry and math

    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
     surla
    -0.75
     raiſ
    -0.75
     itſelf
    -0.71
    Raising
    -0.68
     gddr
    -0.68
     raised
    -0.63
     myſelf
    -0.63
     Raising
    -0.63
    raising
    -0.62
     moul
    -0.62
    POSITIVE LOGITS
     or
    0.59
    stateProvider
    0.52
    InputBorder
    0.52
    createCanvas
    0.50
     of
    0.49
    posedge
    0.47
    /
    0.47
     useSelector
    0.46
    @
    0.45
    pack
    0.44
    Activations Density 0.068%

    No Known Activations