© 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. 3381
    Prev
    Next
    INDEX
    Explanations

    mostly

    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
     aDecoder
    -0.50
     or
    -0.49
    bigsqcup
    -0.49
    oweit
    -0.48
    erapeu
    -0.47
     aftermarket
    -0.46
     mạng
    -0.46
    đồ
    -0.46
    واق
    -0.45
    ellular
    -0.44
    POSITIVE LOGITS
    HtmlAttribute
    0.81
     CreateTagHelper
    0.64
    FormTagHelper
    0.61
    __))
    0.60
    новништво
    0.57
    ंदीखरीदारी
    0.57
    ParallelGroup
    0.56
     BoxDecoration
    0.55
     שוליים
    0.55
     perchè
    0.54
    Activations Density 0.003%

    No Known Activations