© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3291
    Prev
    Next
    INDEX
    Explanations

    Horne

    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
    AddTagHelper
    -0.57
     besluit
    -0.56
     EconPapers
    -0.55
    lierung
    -0.54
    lier
    -0.52
     Wiktionnaire
    -0.52
    jsonwebtoken
    -0.50
    togram
    -0.50
     Junge
    -0.49
     Berber
    -0.49
    POSITIVE LOGITS
     kaynağından
    0.61
    tanleria
    0.57
     that
    0.52
    ArrowToggle
    0.50
     InputDecoration
    0.49
    WriteAttribute
    0.48
    agrama
    0.48
    culable
    0.48
    Istorija
    0.48
    CPtr
    0.47
    Activations Density 0.001%

    No Known Activations