© 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. 12-RES-MATRYOSHKA-DC
    7. 8874
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical values or symbols, particularly those that appear in HTML or coding contexts

    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
     estimés
    -0.78
    aarrggbb
    -0.74
     للاسماء
    -0.73
     \'
    -0.71
    andowski
    -0.69
     مرئيه
    -0.66
    Tikang
    -0.66
    XmlAccessType
    -0.65
    letoe
    -0.64
     InputDecoration
    -0.62
    POSITIVE LOGITS
    errHandler
    0.64
    ’
    0.60
    (({
    0.56
     obicei
    0.54
    います
    0.53
     sikkert
    0.51
    lock
    0.50
    MetaObject
    0.50
    <sup>
    0.50
    到底
    0.50
    Activations Density 0.005%

    No Known Activations