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. 11205
    Prev
    Next
    INDEX
    Explanations

    race

    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
     Coleridge
    -0.85
    ImageContext
    -0.84
    TargetException
    -0.82
     Efq
    -0.80
    grà
    -0.70
    StoryboardSegue
    -0.69
    MLLoader
    -0.68
    Demografie
    -0.68
     StyleSheet
    -0.66
     raiſ
    -0.66
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.56
    enumi
    0.54
    zak
    0.46
    IsPostBack
    0.45
     fines
    0.44
    ודה
    0.43
     problem
    0.42
    ct
    0.41
     hasard
    0.41
     punte
    0.41
    Activations Density 0.205%

    No Known Activations