© 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. 8825
    Prev
    Next
    INDEX
    Explanations

    carving

    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
     carving
    -1.30
     carvings
    -1.09
     carved
    -1.05
     carve
    -0.84
    carved
    -0.77
    RegressionTest
    -0.66
    mybatisplus
    -0.59
    twimg
    -0.57
     nakalista
    -0.56
    basicConfig
    -0.56
    POSITIVE LOGITS
    Demikian
    0.52
    rouvez
    0.50
    styleType
    0.48
     FetchType
    0.48
    shade
    0.48
     CWE
    0.47
    WithMany
    0.47
    Rüyada
    0.47
     gotcha
    0.47
    馃
    0.47
    Activations Density 0.006%

    No Known Activations