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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 711
    Prev
    Next
    INDEX
    Explanations

    knock

    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
     knock
    -1.14
     Knock
    -0.99
     knocking
    -0.98
    knock
    -0.92
    Knock
    -0.89
    nel
    -0.78
     knocks
    -0.77
     knocked
    -0.71
     Kno
    -0.64
    kno
    -0.62
    POSITIVE LOGITS
    ftagPool
    0.86
     незавершена
    0.82
    IsContent
    0.79
    mybatisplus
    0.78
     Paglinawan
    0.73
    ArrowToggle
    0.69
    StoreMessageInfo
    0.66
     архивлан
    0.66
    Pyx
    0.65
    UnusedPrivate
    0.64
    Activations Density 0.018%

    No Known Activations