© 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. 32642
    Prev
    Next
    INDEX
    Explanations

    elements of structured documentation, including steps and outlines related to methods or descriptions of processes

    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
    件
    -0.44
    logische
    -0.42
    ">//
    -0.42
    setPointSize
    -0.42
     undisclosed
    -0.41
    晴
    -0.41
    째
    -0.41
    ----</
    -0.40
    olus
    -0.39
    cloudy
    -0.39
    POSITIVE LOGITS
     للاسماء
    0.84
    "):
    0.80
    ](#
    0.78
    )"),
    0.75
    "),
    0.74
    ."));
    0.74
    )");
    0.73
     =>
    0.72
    ChildScrollView
    0.71
    "))
    0.71
    Activations Density 0.108%

    No Known Activations