© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11732
    Prev
    Next
    INDEX
    Explanations

    bug

    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
     bug
    -1.13
     Bug
    -0.91
     bugs
    -0.80
    Bug
    -0.75
    bug
    -0.73
     Bugs
    -0.70
     insect
    -0.65
     مشين
    -0.62
     buggy
    -0.60
     BUG
    -0.60
    POSITIVE LOGITS
     marinho
    0.59
    jspx
    0.59
     оригіналу
    0.54
    ponses
    0.54
     >=",
    0.52
    carat
    0.51
    phro
    0.50
    YMMV
    0.50
    pexpr
    0.49
     دیکھیے
    0.49
    Activations Density 0.034%

    No Known Activations