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. 0-CLT-HP
    4. 40873
    Prev
    Next
    INDEX
    Explanations

    Mixed language/code/math

    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
    ה
    -1.57
    ָה
    -1.10
    nya
    -0.80
    יה
    -0.77
    the
    -0.62
     ה
    -0.61
    ning
    -0.60
    ned
    -0.58
    מה
    -0.56
    ness
    -0.54
    POSITIVE LOGITS
     CreateTagHelper
    1.10
     autorytatywna
    1.05
     defaultstate
    0.88
    IntoConstraints
    0.85
    ंदीखरीदारी
    0.84
    AccessorTable
    0.84
     propOrder
    0.84
     IBOutlet
    0.82
    )':
    0.82
    moveToFirst
    0.81
    Activations Density 0.131%

    No Known Activations