© 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. 20-CLT-HP
    7. 77194
    Prev
    Next
    INDEX
    Explanations

    pathogens, disease

    np_max-act-logits · 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
    HtmlAttribute
    -0.62
    obacter
    -0.61
    CloseOperation
    -0.59
    外部連結
    -0.57
    robat
    -0.56
    ⎨
    -0.55
    Παραπομπές
    -0.55
    Jereo
    -0.52
    UnusedPrivate
    -0.52
     Attraction
    -0.51
    POSITIVE LOGITS
     inf
    0.60
    ыгана
    0.56
    inf
    0.55
     exogenous
    0.50
     ae
    0.49
    itinéraire
    0.49
     adven
    0.48
    protoc
    0.48
     sap
    0.47
     Commissioners
    0.47
    Activations Density 0.004%

    No Known Activations