© 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. 5-CLT-HP
    7. 96798
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     was
    -0.82
     is
    -0.80
     comes
    -0.69
     has
    -0.67
     ویکی‌آمباردا
    -0.63
     gets
    -0.60
     оригіналу
    -0.57
     occurs
    -0.56
     podría
    -0.56
    apunov
    -0.56
    POSITIVE LOGITS
     mostly
    0.68
     mainly
    0.61
     Include
    0.56
     include
    0.56
     including
    0.55
     includ
    0.54
     chiefly
    0.54
    RemoveAll
    0.52
     חיצוניים
    0.52
     primarily
    0.52
    Activations Density 0.008%

    No Known Activations