© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 75293
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · 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
     Res
    -0.45
    ernan
    -0.43
    anyeol
    -0.43
     res
    -0.43
    pms
    -0.43
    uncher
    -0.42
     Hold
    -0.42
    וויק
    -0.42
     Equ
    -0.41
    __":
    -0.41
    POSITIVE LOGITS
    HtmlAttribute
    0.77
     للاسماء
    0.73
     SwitchCompat
    0.73
    SharedDtor
    0.60
    :✨
    0.60
    <_>
    0.59
    IndentedString
    0.57
    出版年
    0.57
    Хьажоргаш
    0.56
     disponibilités
    0.56
    Activations Density 0.002%

    No Known Activations