© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12033
    Prev
    Next
    INDEX
    Explanations

    on

    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
     armées
    -0.58
     supérieures
    -0.54
     prochaine
    -0.54
     noires
    -0.54
     ouvertes
    -0.53
     nyug
    -0.52
     aisladas
    -0.52
     razon
    -0.50
     planas
    -0.50
     réguli
    -0.49
    POSITIVE LOGITS
    MessageTagHelper
    0.90
    ⓧ
    0.80
    хьтан
    0.79
     Efq
    0.78
    RegressionTest
    0.76
     betweenstory
    0.75
    
    0.75
     itſelf
    0.73
    клопе
    0.70
     useAppContext
    0.70
    Activations Density 0.017%

    No Known Activations