© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 241
    Prev
    Next
    INDEX
    Explanations

    thresholds or criteria for measurement comparisons in data analysis

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     AssemblyCulture
    -0.37
     hal
    -0.35
     spiral
    -0.35
     roll
    -0.34
     flags
    -0.34
    Flags
    -0.34
     fes
    -0.34
    IBAction
    -0.33
     fact
    -0.33
    AddTagHelper
    -0.33
    POSITIVE LOGITS
     than
    0.88
     THAN
    0.86
    beyond
    0.79
    Than
    0.78
     BEYOND
    0.77
    geq
    0.77
    Beyond
    0.77
    YOND
    0.76
     beyond
    0.75
     Beyond
    0.75
    Activations Density 1.565%

    No Known Activations