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. 1-CLT-HP
    4. 12778
    Prev
    Next
    INDEX
    Explanations

    claimed

    np_max-act · 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
    Referencie
    -0.58
    HomeAsUpEnabled
    -0.53
     straff
    -0.52
    BagLayout
    -0.51
    intellij
    -0.50
     دیکھیے
    -0.50
    izable
    -0.49
    plt
    -0.48
    Jereo
    -0.46
    parsedMessage
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.63
     ujednoznacz
    0.58
    bukkit
    0.56
    ConstraintMaker
    0.54
     متحده
    0.53
    //
    0.53
     essence
    0.52
    IANGLES
    0.51
    最快更新
    0.50
     sparks
    0.50
    Activations Density 0.019%

    No Known Activations