© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75642
    Prev
    Next
    INDEX
    Explanations

    Code and uncommon terms

    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
    __":
    -0.81
    __':
    -0.73
    IUrlHelper
    -0.71
    parsedMessage
    -0.65
    原始内容存档于
    -0.62
    __':
    -0.60
    richTextPanel
    -0.60
    __":
    -0.59
    iterranée
    -0.59
     ویکی‌آمباردا
    -0.59
    POSITIVE LOGITS
    +#+#
    0.75
    DoubleQuotes
    0.50
    тт
    0.44
    itigen
    0.42
    parti
    0.41
    strSql
    0.41
    hatan
    0.40
    /******/
    0.40
    has
    0.40
    internalType
    0.39
    Activations Density 0.000%

    No Known Activations