Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73976
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    LookAnd
    -0.85
    InjectAttribute
    -0.79
     beginnetje
    -0.69
     <=",
    -0.67
     Roskov
    -0.66
     Мексичка
    -0.66
    RegistryLite
    -0.66
    IsContent
    -0.65
     NKC
    -0.64
     مرئيه
    -0.63
    POSITIVE LOGITS
    seamnă
    0.50
    toBeTruthy
    0.47
     Tema
    0.46
    streng
    0.45
    tower
    0.44
    νομα
    0.44
    سياسي
    0.43
    atimes
    0.42
    humanité
    0.41
    Tema
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.