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. 74189
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    intios
    -0.65
    FormTagHelper
    -0.65
    quelize
    -0.63
    فایل‌لار
    -0.61
    TestTools
    -0.60
    UnknownFields
    -0.60
     мәкал
    -0.60
     createState
    -0.60
    oprot
    -0.59
     Савезне
    -0.58
    POSITIVE LOGITS
    KommentareTeilen
    0.49
     nakalista
    0.48
     OG
    0.47
    vistar
    0.45
    */].
    0.42
    Hướng
    0.41
    SourceChecksum
    0.40
    one
    0.39
     please
    0.38
    OG
    0.38
    Activations Density 0.002%

    No Known Activations