© 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. 94647
    Prev
    Next
    INDEX
    Explanations

    law

    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
    ning
    -1.07
     controller
    -0.93
     privilege
    -0.85
     controllers
    -0.84
     Controller
    -0.83
     discrimination
    -0.82
    controller
    -0.82
    Controller
    -0.79
    NING
    -0.78
     duty
    -0.77
    POSITIVE LOGITS
     Sunda
    0.54
     mues
    0.52
     سكانية
    0.52
     fidèles
    0.52
    chord
    0.51
    ựng
    0.50
    STC
    0.50
     fidèle
    0.50
    MeasureSpec
    0.49
    ⁄
    0.49
    Activations Density 0.077%

    No Known Activations