© 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. 5-CLT-HP
    7. 92362
    Prev
    Next
    INDEX
    Explanations

    nonchal

    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
    TintMode
    -0.73
    +:+
    -0.70
     defaultstate
    -0.69
    Personensuche
    -0.68
     rospy
    -0.67
    DotNetBar
    -0.64
    >`
    -0.63
    BeginContext
    -0.61
    ReusableCell
    -0.61
    ArrowToggle
    -0.60
    POSITIVE LOGITS
    is
    0.62
    ical
    0.54
    æs
    0.49
    esp
    0.49
    pec
    0.48
    ica
    0.46
    pi
    0.46
    apl
    0.45
    CEL
    0.45
    SqlParameter
    0.45
    Activations Density 0.000%

    No Known Activations