© 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. 91036
    Prev
    Next
    INDEX
    Explanations

    novel

    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
    noise
    -1.02
     noise
    -0.89
    novel
    -0.89
    nesses
    -0.87
     Novel
    -0.86
    ness
    -0.85
     novel
    -0.84
    Noise
    -0.83
     novels
    -0.79
    Novel
    -0.79
    POSITIVE LOGITS
    таратура
    0.57
     dimaksud
    0.52
     tarko
    0.49
    /******/
    0.48
     in
    0.47
    Voci
    0.45
     assim
    0.45
    ContainsKey
    0.43
    Зноскі
    0.43
     atlik
    0.43
    Activations Density 0.153%

    No Known Activations