© 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. 4-CLT-HP
    7. 1028
    Prev
    Next
    INDEX
    Explanations

    infections

    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
     infection
    -0.65
     infections
    -0.59
    infec
    -0.58
    parsedMessage
    -0.57
    Искәрмәләр
    -0.57
    Infection
    -0.56
    جغرافيا
    -0.55
    AddTagHelper
    -0.54
    masks
    -0.52
    hésite
    -0.52
    POSITIVE LOGITS
     Concorde
    0.56
     Andromeda
    0.52
     estatales
    0.51
     judiciales
    0.50
     IOError
    0.49
     comerciais
    0.49
     AppBundle
    0.48
     Comfor
    0.48
     MOA
    0.48
     fuit
    0.48
    Activations Density 0.006%

    No Known Activations