© 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. 0-CLT-HP
    7. 44121
    Prev
    Next
    INDEX
    Explanations

    paper

    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
     
    -0.57
     the
    -0.54
     in
    -0.50
     mogen
    -0.48
     ?
    -0.48
    .
    -0.48
     [
    -0.48
     La
    -0.46
     (
    -0.46
     n
    -0.46
    POSITIVE LOGITS
    SharedDtor
    1.02
     Савезне
    0.98
    sizeCache
    0.96
     disambiguazione
    0.94
    الإنجليزية
    0.93
    IUrlHelper
    0.93
    енча
    0.91
     nakalista
    0.88
     itſelf
    0.88
    ſelves
    0.86
    Activations Density 0.118%

    No Known Activations