© 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. 5-CLT-HP
    7. 93981
    Prev
    Next
    INDEX
    Explanations

    medical diagnoses

    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
    ADVERTISEMENT
    -0.59
    saraba
    -0.57
     PyTuple
    -0.52
     quads
    -0.51
     receding
    -0.50
     saites
    -0.49
    MLLoader
    -0.49
     overclock
    -0.48
    PageModule
    -0.48
    PreInfinity
    -0.48
    POSITIVE LOGITS
    basicConfig
    0.56
    RenderAtEndOf
    0.56
    EnableWeb
    0.55
    oneph
    0.54
     بيها
    0.52
    annotate
    0.51
    bans
    0.51
    ETHING
    0.50
    NOPQRST
    0.50
    nass
    0.50
    Activations Density 0.004%

    No Known Activations