© 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. 8725
    Prev
    Next
    INDEX
    Explanations

    oxides

    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
     oxides
    -1.16
     oxide
    -1.06
     Oxide
    -0.86
    phide
    -0.83
     sulphide
    -0.73
    >>()
    -0.69
     sulfide
    -0.68
     متعلقه
    -0.67
    __':
    -0.66
     Krone
    -0.60
    POSITIVE LOGITS
    最快更新
    0.48
    uedes
    0.48
    pulumi
    0.45
    dillera
    0.44
    ävän
    0.43
    ContentAlignment
    0.43
    lottesville
    0.42
     fact
    0.41
    edoc
    0.40
    васто
    0.40
    Activations Density 0.017%

    No Known Activations