© 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. 69
    Prev
    Next
    INDEX
    Explanations

    repetition, frequency

    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
     CreateTagHelper
    -0.88
     kasarigan
    -0.88
     Савезне
    -0.77
    KommentareTeilen
    -0.71
    EndInit
    -0.70
    PyExc
    -0.69
    WebElementEntity
    -0.69
    AccessorTable
    -0.68
     AssemblyCulture
    -0.68
     >=",
    -0.66
    POSITIVE LOGITS
    ,
    0.55
    spunk
    0.44
     to
    0.42
    êm
    0.40
     arreg
    0.39
    ="#"><
    0.38
    кобрита
    0.37
     -
    0.37
     לקבל
    0.37
     ویکی‌پدیا
    0.36
    Activations Density 0.003%

    No Known Activations