© 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. 16045
    Prev
    Next
    INDEX
    Explanations

    while

    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
     we
    -1.23
     our
    -0.90
    we
    -0.90
     ourselves
    -0.88
    We
    -0.75
     мы
    -0.73
     unseres
    -0.73
    我們
    -0.71
    مصادر
    -0.70
    我们在
    -0.69
    POSITIVE LOGITS
    IUrlHelper
    0.50
    IndentedString
    0.49
     russes
    0.46
    ImageContext
    0.44
    ighorn
    0.43
    ibouti
    0.42
     breezes
    0.42
    ρους
    0.42
    NOPQRST
    0.41
     officials
    0.41
    Activations Density 0.009%

    No Known Activations