© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6112
    Prev
    Next
    INDEX
    Explanations

    content related to code snippets and programming structures

    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
    Negative Logits
     Мексичка
    -1.00
    enterOuterAlt
    -0.98
    sizeCache
    -0.92
    webElementXpaths
    -0.90
    AddTagHelper
    -0.89
    haustible
    -0.89
    sedown
    -0.87
    AddHtmlAttribute
    -0.85
    ьаж
    -0.85
    (!__
    -0.82
    POSITIVE LOGITS
    at
    0.50
     up
    0.50
    as
    0.49
    an
    0.49
    de
    0.48
    par
    0.47
     later
    0.46
     over
    0.46
    ale
    0.45
    in
    0.45
    Activations Density 0.357%

    No Known Activations