© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10408
    Prev
    Next
    INDEX
    Explanations

    biology/chemistry/medicine

    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
    WebVitals
    -0.78
     avoient
    -0.69
     étoient
    -0.69
     purpoſe
    -0.67
     itſelf
    -0.66
     Anſ
    -0.63
     Armory
    -0.62
     kombat
    -0.61
    
    -0.60
     Abonnez
    -0.60
    POSITIVE LOGITS
    Hentet
    0.58
    adaptiveStyles
    0.57
    httphttps
    0.56
    ingu
    0.55
     alla
    0.54
    ér
    0.50
     check
    0.50
     pod
    0.49
    RICAL
    0.49
    cen
    0.48
    Activations Density 0.052%

    No Known Activations