© 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. 35
    Prev
    Next
    INDEX
    Explanations

    statistical terms and phrases related to significance in research findings

    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
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.85
     gsm
    -0.73
    OGND
    -0.73
     houſe
    -0.73
     OFDb
    -0.72
     queſta
    -0.72
    ſelf
    -0.67
     ſche
    -0.67
    IUrlHelper
    -0.67
    majánló
    -0.66
    POSITIVE LOGITS
     significantly
    0.54
     nearly
    0.53
     overall
    0.52
     tertinggi
    0.50
     compared
    0.49
     increased
    0.47
     decrease
    0.46
     markedly
    0.45
     deutlich
    0.44
     hampir
    0.43
    Activations Density 12.558%

    No Known Activations