© 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. 2826
    Prev
    Next
    INDEX
    Explanations

    pandas and numpy import

    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
     متعلقه
    -0.70
     estimés
    -0.66
    المناصب
    -0.65
     sumpay
    -0.65
     كومونز
    -0.63
     Walkover
    -0.63
    Hentet
    -0.63
    awtextra
    -0.61
    Šaltiniai
    -0.61
    mybatisplus
    -0.61
    POSITIVE LOGITS
     bars
    0.44
    astify
    0.43
     Fø
    0.39
     equalization
    0.39
     carni
    0.38
    Фо
    0.38
    arta
    0.38
    jamientos
    0.38
    áp
    0.38
    Isra
    0.37
    Activations Density 0.014%

    No Known Activations