© 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. 4144
    Prev
    Next
    INDEX
    Explanations

    references to DOM elements or the DOM itself

    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
    ValueStyle
    -0.69
    Παραπομπές
    -0.58
    Билгалдахарш
    -0.55
    withIdentifier
    -0.53
     coi
    -0.49
    Dropout
    -0.48
    ushman
    -0.47
     garansi
    -0.47
    grand
    -0.47
    ondern
    -0.47
    POSITIVE LOGITS
    dom
    3.45
    Dom
    3.13
     dom
    3.08
     Dom
    2.88
     DOM
    2.88
    DOM
    2.83
     domestic
    2.39
     Domestic
    2.38
    Domestic
    2.38
    domestic
    2.30
    Activations Density 0.009%

    No Known Activations