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. 11307
    Prev
    Next
    INDEX
    Explanations

    list

    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
    XMLSchema
    -0.70
    ancers
    -0.68
     kasarigan
    -0.68
     tuyo
    -0.65
     חיצוניים
    -0.65
    DoubleQuotes
    -0.65
     Abonnez
    -0.63
    quels
    -0.61
    thâu
    -0.61
     collars
    -0.60
    POSITIVE LOGITS
    <bos>
    0.56
     tracing
    0.43
     of
    0.40
     I
    0.38
     remp
    0.37
     We
    0.36
    ريل
    0.35
    DJANGO
    0.35
    cari
    0.35
    editForm
    0.35
    Activations Density 0.007%

    No Known Activations