© 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. 1-CLT-HP
    7. 11699
    Prev
    Next
    INDEX
    Explanations

    Viruses and 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
    CV
    -0.65
    +#+#
    -0.60
     resourceCulture
    -0.60
     CV
    -0.50
     purse
    -0.45
    corsi
    -0.43
    ImageBackground
    -0.43
    isição
    -0.41
    RetentionPolicy
    -0.41
     twain
    -0.40
    POSITIVE LOGITS
    elemField
    0.76
     onItemClick
    0.60
    новниш
    0.57
    FIG
    0.55
    reign
    0.53
    posedge
    0.52
    bail
    0.51
    iprot
    0.51
    ">//
    0.51
    doise
    0.51
    Activations Density 0.050%

    No Known Activations