© 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. 5-CLT-HP
    7. 4806
    Prev
    Next
    INDEX
    Explanations

    viral 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
     stället
    -0.60
     autorytatywna
    -0.59
    :✨
    -0.59
    FormTagHelper
    -0.57
     pauvreté
    -0.56
    ictionary
    -0.55
     mauvaises
    -0.54
     surla
    -0.53
    ῖν
    -0.53
     ostavi
    -0.52
    POSITIVE LOGITS
     CMO
    0.54
     neon
    0.51
     childhood
    0.49
     sparks
    0.47
    RIX
    0.47
     rash
    0.47
     infection
    0.47
    MouseEvent
    0.47
     meningitis
    0.47
     outbreaks
    0.46
    Activations Density 0.014%

    No Known Activations