Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74336
    Prev
    Next
    INDEX
    Explanations

    clo

    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
     الحره
    -0.91
    Personensuche
    -0.69
    سطس
    -0.65
    SequentialGroup
    -0.60
    AxisAlignment
    -0.57
    QtWidgets
    -0.56
    [--
    -0.55
    HomeAsUp
    -0.55
    脚注の使い方
    -0.54
    وحة
    -0.52
    POSITIVE LOGITS
    rungsseite
    0.75
     CreateTagHelper
    0.52
    WebServlet
    0.50
    createServer
    0.47
    XmlAccessType
    0.46
    delwed
    0.45
     springfox
    0.45
     Wikimedijinoj
    0.44
    jspx
    0.44
     "..\..\..\
    0.43
    Activations Density 0.003%

    No Known Activations