© 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. 20-CLT-HP
    7. 71480
    Prev
    Next
    INDEX
    Explanations

    food and sweets

    np_max-act-logits · 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
    CodeAttribute
    -0.77
    تقاوى
    -0.66
    Portail
    -0.64
     surla
    -0.64
     ویکی‌پدیا
    -0.62
    BufferException
    -0.61
    السكان
    -0.61
    TagHelper
    -0.58
    AntiForgeryToken
    -0.57
     ویکی‌پدی
    -0.56
    POSITIVE LOGITS
     lol
    0.77
     Hari
    0.63
     régl
    0.62
     snippetHide
    0.57
     min
    0.57
     hard
    0.56
    Hari
    0.54
     Hard
    0.54
     conf
    0.53
     gummies
    0.53
    Activations Density 0.001%

    No Known Activations