© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95442
    Prev
    Next
    INDEX
    Explanations

    Infection

    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
    -1.61
     Infection
    -1.61
     infected
    -1.52
    infection
    -1.52
     infect
    -1.51
    Infection
    -1.48
    infected
    -1.43
     Infected
    -1.41
     infecting
    -1.31
     infections
    -1.29
    POSITIVE LOGITS
    .
    0.81
    ,
    0.63
     (
    0.59
     with
    0.57
     .
    0.57
     
    0.56
     by
    0.56
     and
    0.52
    ↵↵
    0.52
    v
    0.51
    Activations Density 0.567%

    No Known Activations