© 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. 5-CLT-HP
    7. 91228
    Prev
    Next
    INDEX
    Explanations

    urine/urinalysis

    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
    anteen
    -0.49
    Genial
    -0.45
    Director
    -0.43
     engraçadas
    -0.43
    éclairage
    -0.42
     publier
    -0.42
     ilustración
    -0.42
    lindungan
    -0.41
     Director
    -0.41
    ्रीय
    -0.41
    POSITIVE LOGITS
    ysis
    0.71
    yses
    0.60
    y
    0.59
    yz
    0.58
    bum
    0.58
     AssemblyCulture
    0.57
     متعلقه
    0.57
    yot
    0.56
    yta
    0.53
    yste
    0.51
    Activations Density 0.002%

    No Known Activations