© 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. 94117
    Prev
    Next
    INDEX
    Explanations

    detail

    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
     vér
    -0.56
     rentals
    -0.52
    <bos>
    -0.51
     Stroh
    -0.50
     الأصل
    -0.50
    Werdegang
    -0.49
    下载附件
    -0.48
     soste
    -0.48
     препратки
    -0.48
     key
    -0.47
    POSITIVE LOGITS
    JpaRepository
    0.60
    ressee
    0.60
    Хро
    0.57
    MeasureSpec
    0.54
     оригіналу
    0.54
     autorytatywna
    0.54
    KommentareTeilen
    0.54
    UnknownFieldSet
    0.52
    iedenis
    0.50
    resar
    0.50
    Activations Density 0.002%

    No Known Activations