© 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. 0-CLT-HP
    7. 1111
    Prev
    Next
    INDEX
    Explanations

    mono

    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
    making
    -0.85
     mono
    -0.70
    mono
    -0.70
     Mono
    -0.68
    DoubleQuotes
    -0.64
    Hentet
    -0.64
    Making
    -0.62
     making
    -0.61
    MAKING
    -0.60
    i
    -0.59
    POSITIVE LOGITS
    انجليز
    0.58
    actéristique
    0.57
    setupUi
    0.57
    slate
    0.56
     carreaux
    0.55
     varandra
    0.55
     geslacht
    0.54
     fianco
    0.54
    msgSender
    0.53
     فريبيس
    0.52
    Activations Density 0.156%

    No Known Activations