© 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. 25532
    Prev
    Next
    INDEX
    Explanations

    structured elements, particularly various types of mathematical syntax and notation

    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
    eſt
    -0.80
    iastical
    -0.77
    ''');
    -0.76
     IBOutlet
    -0.75
    ".$_
    -0.75
    )['
    -0.75
    CloseOperation
    -0.74
    gnancy
    -0.73
    AVY
    -0.73
    elfare
    -0.73
    POSITIVE LOGITS
    {
    0.84
    er
    0.77
     {
    0.74
    {
    0.71
    <strong>
    0.68
    numerusform
    0.67
    {}{
    0.64
    RTLD
    0.64
    ers
    0.63
    Rüyada
    0.62
    Activations Density 0.066%

    No Known Activations