© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    medical patients/subjects

    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
     ô
    -0.44
     ful
    -0.43
     sample
    -0.41
    alog
    -0.41
     ley
    -0.40
     direct
    -0.39
    ambar
    -0.39
     full
    -0.39
    full
    -0.38
     regular
    -0.38
    POSITIVE LOGITS
     HasFactory
    0.99
    StoryboardSegue
    0.97
     CreateTagHelper
    0.96
     ProtoMessage
    0.95
    StructEnd
    0.91
    XMLSchema
    0.89
     للمعارف
    0.88
    BufferException
    0.88
    MLLoader
    0.82
    SharedDtor
    0.82
    Activations Density 0.004%

    No Known Activations