© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5536
    Prev
    Next
    INDEX
    Explanations

    references to specific HTML or script elements, especially attributes like "integrity" and "crossorigin" within code snippets and tags

    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
    DS
    -0.54
     Humph
    -0.54
     Ration
    -0.53
     Sni
    -0.52
     Intelli
    -0.51
     tachy
    -0.51
     ellips
    -0.50
     apprehen
    -0.50
     getItemId
    -0.49
    Tage
    -0.49
    POSITIVE LOGITS
    jsxFileName
    0.74
    Παραπομπές
    0.66
    nonatomic
    0.60
    期刊论文
    0.58
    HasForeignKey
    0.57
    tvguidetime
    0.57
    ]){
    0.57
    httphttps
    0.56
     EconPapers
    0.56
    互联网档案馆
    0.54
    Activations Density 0.856%

    No Known Activations