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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12105
    Prev
    Next
    INDEX
    Explanations

    game

    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
    الحياه
    -0.67
    ValueStyle
    -0.61
     autorytatywna
    -0.59
     clearColor
    -0.56
    Perman
    -0.55
     ویکی‌پدیای
    -0.51
     préc
    -0.51
    tawesome
    -0.51
    après
    -0.50
     morire
    -0.50
    POSITIVE LOGITS
    ArgsConstructor
    0.59
     noqa
    0.57
    AutoField
    0.56
     Signalez
    0.54
     Projektu
    0.51
     noDo
    0.50
    DebuggerNonUser
    0.49
    Personensuche
    0.48
    chromedriver
    0.48
    runApp
    0.47
    Activations Density 0.047%

    No Known Activations