© 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. 96457
    Prev
    Next
    INDEX
    Explanations

    Traditional chinese 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
     فريبيس
    -0.67
    pushFollow
    -0.62
     MonoBehaviour
    -0.57
     Nguy
    -0.56
    sonaro
    -0.56
     GenerationType
    -0.55
    NOPQRST
    -0.54
     defaultstate
    -0.51
     Audiodateien
    -0.50
     HttpNotFound
    -0.50
    POSITIVE LOGITS
     kasarigan
    0.68
    :✨
    0.57
     himo
    0.52
     дописавши
    0.52
     herv
    0.51
    WireFormatLite
    0.51
    ponses
    0.50
    Wallis
    0.49
     RISERV
    0.48
     sauvages
    0.48
    Activations Density 0.007%

    No Known Activations