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. 12831
    Prev
    Next
    INDEX
    Explanations

    do (as in, questions)

    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
     homework
    -0.66
     larmes
    -0.57
    mailto
    -0.48
     equipaje
    -0.48
     réguli
    -0.47
     automatiques
    -0.46
    JsonValue
    -0.45
     prête
    -0.45
     culturelles
    -0.44
     âmes
    -0.43
    POSITIVE LOGITS
    ">//
    0.81
     betweenstory
    0.77
    RegressionTest
    0.71
    ″]
    0.71
    رشف
    0.63
     '{@
    0.63
    getDescriptor
    0.63
    enderror
    0.60
    AddHtmlAttribute
    0.60
     propOrder
    0.58
    Activations Density 0.214%

    No Known Activations