© 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. 0-CLT-HP
    7. 94090
    Prev
    Next
    INDEX
    Explanations

    viruses/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
    thâu
    -0.96
     Infection
    -0.94
     propOrder
    -0.89
    parsedMessage
    -0.83
    awtextra
    -0.81
     @"/
    -0.80
     infection
    -0.79
     Infections
    -0.79
    Infection
    -0.77
    ftagPool
    -0.77
    POSITIVE LOGITS
    n
    0.59
    G
    0.53
    A
    0.51
    en
    0.47
     useParams
    0.46
    if
    0.45
    I
    0.44
    as
    0.43
    g
    0.43
    s
    0.43
    Activations Density 0.336%

    No Known Activations