© 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. 1-CLT-HP
    7. 9902
    Prev
    Next
    INDEX
    Explanations

    nose

    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
     nose
    -1.15
     Nose
    -1.08
    nose
    -1.07
    Nose
    -0.95
     noses
    -0.89
    Datuak
    -0.71
    ness
    -0.70
    nical
    -0.68
    antaranya
    -0.67
     nariz
    -0.65
    POSITIVE LOGITS
    qrstuvwxyz
    0.47
    let
    0.45
     pimiento
    0.45
    toMatchSnapshot
    0.44
     Stanton
    0.44
    able
    0.42
     Schengen
    0.42
    americana
    0.41
    out
    0.40
    getOut
    0.40
    Activations Density 0.011%

    No Known Activations