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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15263
    Prev
    Next
    INDEX
    Explanations

    time

    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
     of
    -0.70
     nahilalakip
    -0.65
    damento
    -0.65
    ESSO
    -0.60
    ITHUB
    -0.56
     vers
    -0.49
     fide
    -0.49
     ked
    -0.49
    ustand
    -0.49
     he
    -0.48
    POSITIVE LOGITS
    GOTREF
    0.68
    +#+#
    0.65
     linkovi
    0.62
    MLLoader
    0.60
    WindowConstants
    0.60
     ChromeDriver
    0.59
     cerimonia
    0.56
    DoubleQuotes
    0.56
    DriverManager
    0.55
     ejus
    0.54
    Activations Density 0.027%

    No Known Activations