© 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. 4313
    Prev
    Next
    INDEX
    Explanations

    Beginning phrases of documents

    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
    клопе
    -0.60
     Centre
    -0.54
    jsdelivr
    -0.51
     pinulongan
    -0.50
    valently
    -0.48
     محفوظة
    -0.48
     SwitchCompat
    -0.48
    Tembelea
    -0.47
     Center
    -0.47
    OfWork
    -0.47
    POSITIVE LOGITS
    Fazit
    0.57
    nocache
    0.53
     факт
    0.53
     itſelf
    0.52
    Conclusie
    0.52
    ｀
    0.51
     médicaux
    0.51
     mikä
    0.51
    ParallelGroup
    0.50
     peine
    0.49
    Activations Density 0.001%

    No Known Activations