© 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. 20-CLT-HP
    7. 74747
    Prev
    Next
    INDEX
    Explanations

    code, URLs, foreign languages

    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
    Not in Any Lists

    No Comments

    Negative Logits
    SCRIP
    -0.48
     Meksiku
    -0.48
     Fib
    -0.48
    Piper
    -0.48
     psa
    -0.47
    стероид
    -0.47
    ebus
    -0.47
     tafel
    -0.46
    calaure
    -0.46
    dstuk
    -0.46
    POSITIVE LOGITS
    tagHelperRunner
    0.69
     ویکی‌پدیا
    0.66
    Παραπομπές
    0.60
    NUMX
    0.56
     preghiera
    0.54
    CloseOperation
    0.54
    ScopeManager
    0.54
     Accord
    0.54
    原始内容存档于
    0.53
    SuppressLint
    0.53
    Activations Density 0.000%

    No Known Activations