© 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. 3995
    Prev
    Next
    INDEX
    Explanations

    instances of CSS transform properties related to rotation across different vendor prefixes

    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
    SequentialGroup
    -0.77
     Wied
    -0.68
     Chwiliwch
    -0.68
     따
    -0.65
    Obrázky
    -0.64
    diale
    -0.64
    Expedia
    -0.64
    TMR
    -0.62
     areia
    -0.62
     camels
    -0.61
    POSITIVE LOGITS
     transform
    2.80
    transform
    2.72
     Transform
    2.50
    Transform
    2.48
     transformation
    2.47
     Transformation
    2.30
     transforming
    2.30
     transformations
    2.27
     transforms
    2.25
     transformed
    2.20
    Activations Density 0.024%

    No Known Activations