© 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. 1-CLT-HP
    7. 16181
    Prev
    Next
    INDEX
    Explanations

    oxygen

    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
    Negative Logits
     auroit
    -0.73
     colorés
    -0.72
    expandindo
    -0.70
    ValueStyle
    -0.70
     déchir
    -0.69
     chrétiens
    -0.68
     feroit
    -0.67
     avoient
    -0.67
     chré
    -0.66
     démocr
    -0.65
    POSITIVE LOGITS
     Serra
    0.48
    alerie
    0.45
     ber
    0.44
     ranks
    0.43
     ranges
    0.42
     charge
    0.42
     Lance
    0.42
     GLFW
    0.42
     cons
    0.42
     en
    0.42
    Activations Density 0.019%

    No Known Activations