© 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. 0-RES-MATRYOSHKA-DC
    7. 10781
    Prev
    Next
    INDEX
    Explanations

    quantify the degree to which a certain variable or measurement is present or expressed

    oai_token-act-pair · gpt-4.1-nano
    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
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.57
    PostExecute
    -0.52
    ulas
    -0.51
    ignty
    -0.50
    Insee
    -0.50
    HomeAsUpEnabled
    -0.49
     Hallen
    -0.49
    vnd
    -0.49
    AndEndTag
    -0.49
    fandom
    -0.49
    POSITIVE LOGITS
     quantify
    1.09
     disqual
    1.01
    MigrationBuilder
    0.79
     Chwiliwch
    0.77
     disqualified
    0.77
     censiti
    0.73
    ValueStyle
    0.73
     anhydride
    0.69
     (^
    0.68
    opic
    0.67
    Activations Density 0.036%

    No Known Activations