© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5821
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific CSS style attributes related to element dimensions

    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
     height
    -1.68
     Height
    -1.48
    Height
    -1.41
    height
    -1.34
     HEIGHT
    -1.34
     heights
    -1.31
    HEIGHT
    -1.27
    Heights
    -1.06
     getHeight
    -0.99
     altura
    -0.99
    POSITIVE LOGITS
    width
    1.51
     width
    1.07
    WIDTH
    1.02
    Width
    0.96
     Width
    0.86
     WIDTH
    0.83
     widths
    0.82
    widths
    0.80
     spermato
    0.66
    宽度
    0.61
    Activations Density 0.041%

    No Known Activations