© 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. 15958
    Prev
    Next
    INDEX
    Explanations

    designed

    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
     organisation
    -0.61
     behaviour
    -0.59
     programme
    -0.59
     colour
    -0.57
     utilisation
    -0.56
     programmes
    -0.55
     armour
    -0.55
     Всё
    -0.54
     centre
    -0.54
    Всё
    -0.54
    POSITIVE LOGITS
    +#+#
    1.01
     nahilalakip
    0.87
     propOrder
    0.77
     وتسجيلات
    0.73
     dAtA
    0.69
     <=",
    0.68
     ErrIntOverflow
    0.66
     Nacionales
    0.65
    InteropServices
    0.63
     defaultstate
    0.63
    Activations Density 0.010%

    No Known Activations