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. 74062
    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
     propOrder
    -0.67
    bürgermeister
    -0.65
    ंदीखरीदारी
    -0.62
     chrétiens
    -0.60
     chaude
    -0.59
    UnsafeEnabled
    -0.57
     hiér
    -0.56
     carreaux
    -0.55
    UrlResolution
    -0.55
     varandra
    -0.55
    POSITIVE LOGITS
     stay
    0.53
     working
    0.51
    glDelete
    0.50
    ChildScrollView
    0.50
     with
    0.50
     scattering
    0.50
     works
    0.49
     POLLUTION
    0.49
     be
    0.49
     work
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.