© 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. 15
    Prev
    Next
    INDEX
    Explanations

    part

    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
    pinMode
    -0.64
     distinct
    -0.56
    UIControlState
    -0.51
    deviantart
    -0.49
     frozen
    -0.49
    兢
    -0.49
    toThrow
    -0.48
    PropertyChanged
    -0.48
     traditional
    -0.48
     small
    -0.48
    POSITIVE LOGITS
    erover
    0.68
    SharedDtor
    0.66
     שוליים
    0.63
     referenties
    0.62
     חיצוניים
    0.60
    Бахар
    0.58
     typelib
    0.58
    出版年
    0.56
     Töchter
    0.54
    MLLoader
    0.53
    Activations Density 0.001%

    No Known Activations