© 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. 4-CLT-HP
    7. 5055
    Prev
    Next
    INDEX
    Explanations

    medical topics

    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
    omyia
    -0.48
    shields
    -0.48
    ectoria
    -0.47
    tableFuture
    -0.47
    windowFixed
    -0.47
     ujednoznacz
    -0.46
    iertamente
    -0.46
    DockStyle
    -0.46
    TypedDataSet
    -0.45
     visiteurs
    -0.45
    POSITIVE LOGITS
    MessageTagHelper
    0.70
     getRule
    0.55
    =$?
    0.54
    lossal
    0.53
     MaterialApp
    0.52
    مدل
    0.52
    !*\
    0.52
     abusers
    0.52
     Prasad
    0.51
     empress
    0.50
    Activations Density 0.004%

    No Known Activations