© 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. 42288
    Prev
    Next
    INDEX
    Explanations

    degrees

    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
     degrees
    -0.71
    degrees
    -0.69
     Faso
    -0.64
     educated
    -0.55
     تضيفلها
    -0.55
    Degrees
    -0.54
     grados
    -0.52
     Degrees
    -0.47
     flecha
    -0.43
     respeito
    -0.42
    POSITIVE LOGITS
    SourceChecksum
    1.03
    slidesToShow
    0.72
    ModelSerializer
    0.72
    sizeCache
    0.68
    matplotlib
    0.67
     @"/
    0.67
     <<<<<<<<<<<<<<
    0.67
    layui
    0.64
    spraak
    0.63
    +:+
    0.62
    Activations Density 1.281%

    No Known Activations