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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40389
    Prev
    Next
    INDEX
    Explanations

    KI

    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
    KI
    -1.76
     KI
    -1.63
    Portale
    -0.64
     Ki
    -0.63
     ki
    -0.60
     ')[
    -0.60
    Viitteet
    -0.60
    Ki
    -0.57
    schild
    -0.57
     MotionEvent
    -0.55
    POSITIVE LOGITS
    lize
    0.56
    setPreferred
    0.54
    setVerticalGroup
    0.52
     Comprometido
    0.50
    ted
    0.49
     cosi
    0.48
    Predecesor
    0.48
     Réalisation
    0.47
    otho
    0.46
     Lumpur
    0.45
    Activations Density 0.745%

    No Known Activations