© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16186
    Prev
    Next
    INDEX
    Explanations

    uz

    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
    Negative Logits
    uz
    -2.31
    UZ
    -1.61
    uza
    -1.13
    uzi
    -1.03
    uze
    -1.02
     uz
    -0.97
    ouz
    -0.96
    uzu
    -0.86
    Uz
    -0.79
    úz
    -0.67
    POSITIVE LOGITS
     Efq
    0.70
     faſt
    0.60
     ſever
    0.57
     Eſ
    0.57
     fevere
    0.56
     jsPsych
    0.55
    CloseOperation
    0.55
    forth
    0.55
     Reſ
    0.54
    حث
    0.53
    Activations Density 0.013%

    No Known Activations