© 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. 93492
    Prev
    Next
    INDEX
    Explanations

    per

    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
    rungsseite
    -0.72
     prossima
    -0.71
     financière
    -0.69
     financières
    -0.68
     militaires
    -0.68
     démocr
    -0.68
     Etats
    -0.67
     religieuses
    -0.67
     colorés
    -0.66
     sauvages
    -0.65
    POSITIVE LOGITS
     given
    0.52
     region
    0.48
     genotype
    0.47
     useNavigate
    0.47
     town
    0.46
     uska
    0.45
     kind
    0.45
    行政区划
    0.45
     device
    0.44
     country
    0.43
    Activations Density 0.001%

    No Known Activations