© 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-RES-MATRYOSHKA-DC
    7. 1336
    Prev
    Next
    INDEX
    Explanations

    references to the CSS property "top" or mentions of positioning elements vertically

    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
    Negative Logits
     Lower
    -1.08
    Lower
    -1.04
     lower
    -0.97
    lower
    -0.93
     LOWER
    -0.85
     lowering
    -0.81
     lowered
    -0.76
    LOWER
    -0.75
     lowers
    -0.74
     raised
    -0.65
    POSITIVE LOGITS
     top
    4.34
    top
    4.22
    Top
    3.91
     Top
    3.91
    TOP
    3.48
     TOP
    3.39
    tops
    2.91
     tops
    2.88
    getTop
    2.59
    トップ
    2.55
    Activations Density 0.453%

    No Known Activations