© 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. 13559
    Prev
    Next
    INDEX
    Explanations

    ges

    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
    EOUS
    -0.56
    oplasty
    -0.48
     olev
    -0.45
    phane
    -0.45
    igné
    -0.44
     Бере
    -0.44
    gery
    -0.44
    cifix
    -0.43
    ặn
    -0.43
     NDL
    -0.43
    POSITIVE LOGITS
    rungsseite
    1.16
     &___
    0.73
    LookAnd
    0.72
    expandindo
    0.68
     ***!
    0.68
    Javadoc
    0.68
     оригіналу
    0.67
    Šaltiniai
    0.67
    PMailer
    0.65
    AndEndTag
    0.64
    Activations Density 0.075%

    No Known Activations