© 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. 1-CLT-HP
    7. 46284
    Prev
    Next
    INDEX
    Explanations

    medical context

    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
    sizeCache
    -0.64
    RegistryLite
    -0.59
     resourceCulture
    -0.57
    enderror
    -0.56
     createState
    -0.54
    Ecotoxicity
    -0.54
     ignition
    -0.52
     Plut
    -0.52
     octave
    -0.52
     jScrollPane
    -0.51
    POSITIVE LOGITS
     CreateTagHelper
    0.60
     ujednoznacz
    0.57
     skär
    0.56
     børn
    0.53
    COUVER
    0.53
     חיצוניים
    0.52
     تانيه
    0.51
     kvinder
    0.50
     hijas
    0.50
     næ
    0.49
    Activations Density 0.043%

    No Known Activations