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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96900
    Prev
    Next
    INDEX
    Explanations

    online

    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
    bewerken
    -0.61
    expandindo
    -0.60
     estimés
    -0.55
     iconTwitter
    -0.54
     ujednoznacz
    -0.52
    netje
    -0.52
     ویکی‌پدیا
    -0.52
     חיצוניים
    -0.50
     trajets
    -0.49
    ">—
    -0.49
    POSITIVE LOGITS
     sources
    0.57
     MainAxisSize
    0.54
    sources
    0.52
     job
    0.50
     Wolff
    0.50
     articles
    0.50
     services
    0.49
     research
    0.49
     articol
    0.49
     resources
    0.48
    Activations Density 0.001%

    No Known Activations