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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19546
    Prev
    Next
    INDEX
    Explanations

    elements related to the state of JavaScript in web browsers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gemeinsame
    -0.57
     uLocal
    -0.57
    IContainer
    -0.56
    StoreMessageInfo
    -0.50
    onatos
    -0.50
     ::=
    -0.48
    roslav
    -0.48
    ----</
    -0.47
     Italijanski
    -0.46
    aliana
    -0.45
    POSITIVE LOGITS
    noscript
    2.50
    CRIPT
    0.74
    AndEndTag
    0.73
    reportWebVitals
    0.73
    <!--[
    0.65
     kaarangay
    0.63
    numerusform
    0.63
     переписи
    0.61
    Geografi
    0.60
     gainera
    0.59
    Activations Density 0.001%

    No Known Activations