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. 74017
    Prev
    Next
    INDEX
    Explanations

    Formal writing

    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
     exception
    -0.71
     &___
    -0.67
     CreateTagHelper
    -0.65
     ModelExpression
    -0.65
    ⓧ
    -0.65
    enumii
    -0.61
    IsMutable
    -0.58
    sidemargin
    -0.57
     possible
    -0.57
    achable
    -0.56
    POSITIVE LOGITS
     the
    1.10
    ofthe
    0.50
    just
    0.45
     just
    0.44
     fédé
    0.43
    onedDateTime
    0.42
     êtes
    0.42
     diamants
    0.41
    rare
    0.41
     ofthe
    0.40
    Activations Density 0.007%

    No Known Activations