© 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. 6-RES-MATRYOSHKA-DC
    7. 1438
    Prev
    Next
    INDEX
    Explanations

    the word "under" modifying a situation or condition

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    脚注の使い方
    -0.95
    __(/*!
    -0.75
    amaged
    -0.70
    ◗
    -0.68
    tagHelperRunner
    -0.66
     באמצעות
    -0.66
    via
    -0.65
    **/
    -0.65
     Pingback
    -0.62
    äumt
    -0.62
    POSITIVE LOGITS
     under
    2.13
    Under
    2.03
     Under
    2.00
    under
    1.91
     UNDER
    1.77
    UNDER
    1.68
     sotto
    1.34
    Bajo
    1.32
     unter
    1.30
     bajo
    1.27
    Activations Density 0.476%

    No Known Activations