© 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. 15712
    Prev
    Next
    INDEX
    Explanations

    udge

    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
    ud
    -1.20
    uds
    -1.09
    UD
    -1.07
    udh
    -1.06
    udy
    -1.05
    uding
    -1.00
    udd
    -0.97
    udi
    -0.93
    ude
    -0.90
    udes
    -0.86
    POSITIVE LOGITS
    ly
    0.60
    tvguidetime
    0.55
    face
    0.54
     Marked
    0.54
    es
    0.52
    нциклопе
    0.52
    jstor
    0.51
     CreateTagHelper
    0.50
    ते
    0.49
    back
    0.48
    Activations Density 0.435%

    No Known Activations