© 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. 96649
    Prev
    Next
    INDEX
    Explanations

    the

    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
    AntiForgeryToken
    -0.68
     newOwner
    -0.61
     PartialEq
    -0.61
    !")
    -0.60
     ویکی‌پدیا
    -0.60
     bezeichneter
    -0.58
    localctx
    -0.58
    FieldBuilder
    -0.57
    $.
    -0.56
     Anſ
    -0.55
    POSITIVE LOGITS
     ddelweddau
    0.66
    ⓧ
    0.64
     cost
    0.58
    PYX
    0.52
     незавершена
    0.51
     organised
    0.51
     MainAxisSize
    0.48
    äsident
    0.47
     joined
    0.46
    sieme
    0.46
    Activations Density 0.001%

    No Known Activations