© 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. 12954
    Prev
    Next
    INDEX
    Explanations

    technology

    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
     فريبيس
    -0.68
    ReferenceEquals
    -0.65
    دانشنامهٔ
    -0.65
     оригіналу
    -0.63
    Rhestr
    -0.62
    ArrowToggle
    -0.59
    UnsafeEnabled
    -0.58
    Географи
    -0.56
    contentLoaded
    -0.54
    PyExc
    -0.54
    POSITIVE LOGITS
    izable
    0.59
    Externé
    0.58
    ization
    0.57
    eau
    0.57
    ial
    0.56
    ized
    0.55
    ize
    0.54
    ised
    0.52
     duster
    0.52
    izations
    0.52
    Activations Density 0.037%

    No Known Activations