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. 20-CLT-HP
    4. 74139
    Prev
    Next
    INDEX
    Explanations

    describing actions

    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
     the
    -0.76
     a
    -0.73
    CppCodeGen
    -0.69
     Italijani
    -0.68
    Each
    -0.68
    retudo
    -0.65
    UnusedPrivate
    -0.64
    Setiap
    -0.64
    Otherwise
    -0.63
    قایناق‌لار
    -0.63
    POSITIVE LOGITS
     one
    0.52
     otra
    0.41
    tagHelper
    0.41
     otro
    0.39
    data
    0.39
    Software
    0.38
     another
    0.38
     یکی
    0.38
    webElement
    0.38
    gas
    0.37
    Activations Density 0.008%

    No Known Activations