© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14819
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
     failed
    -0.50
    oung
    -0.48
    ANTLR
    -0.46
     Young
    -0.46
     failure
    -0.45
    enscha
    -0.44
    Young
    -0.43
     sheer
    -0.42
     task
    -0.42
    oula
    -0.41
    POSITIVE LOGITS
     Мексичка
    0.75
     HasFactory
    0.72
    PMailer
    0.66
    FormTagHelper
    0.66
    routeProvider
    0.65
    ExtendWith
    0.63
    TagMode
    0.63
    CodedInputStream
    0.62
    zielle
    0.62
    ArrowToggle
    0.60
    Activations Density 0.035%

    No Known Activations