© 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. 11610
    Prev
    Next
    INDEX
    Explanations

    general topics and descriptions

    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
     oreilles
    -0.63
    AddTagHelper
    -0.60
     réus
    -0.57
    তথ্যসূত্র
    -0.57
     AssemblyCulture
    -0.57
    Tikang
    -0.56
    ̈́
    -0.55
    ///</
    -0.54
    出版年
    -0.54
     bēr
    -0.52
    POSITIVE LOGITS
     typelib
    0.70
    //
    0.68
    aians
    0.59
    titleMargin
    0.55
     Polynesia
    0.54
     Normdatei
    0.53
    AsyncResult
    0.49
     المعيارى
    0.49
     חיצוניים
    0.49
    consumed
    0.48
    Activations Density 0.029%

    No Known Activations