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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73987
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ISupport
    -0.61
    />";
    -0.60
    󠁢
    -0.60
    ViewFeatures
    -0.59
    Obrázky
    -0.56
     ExecuteAsync
    -0.55
     whiteColor
    -0.55
    uesia
    -0.54
    Stuck
    -0.54
     doGet
    -0.53
    POSITIVE LOGITS
    XmlAccessType
    0.51
     propOrder
    0.44
    basicConfig
    0.42
    jsonwebtoken
    0.41
    D
    0.41
    BeginContext
    0.41
     AssemblyProduct
    0.40
    cipl
    0.39
     d
    0.38
    ActivityCompat
    0.38
    Activations Density 0.001%

    No Known Activations