© 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. 5-CLT-HP
    7. 92242
    Prev
    Next
    INDEX
    Explanations

    the

    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
     bezeichneter
    -0.60
     createContext
    -0.60
    Externí
    -0.58
    Биография
    -0.57
    rungsseite
    -0.57
     StatefulWidget
    -0.57
    
    -0.57
     للمعارف
    -0.56
    Personensuche
    -0.55
    RUnlock
    -0.54
    POSITIVE LOGITS
     related
    0.79
     associated
    0.76
     consequent
    0.71
     damit
    0.71
     attendant
    0.66
    complexContent
    0.66
     corresponding
    0.65
     subsequent
    0.64
     concomitant
    0.61
     resultant
    0.60
    Activations Density 0.003%

    No Known Activations