© 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. 2-RES-MATRYOSHKA-DC
    7. 3443
    Prev
    Next
    INDEX
    Explanations

    the presence of formatting or structural elements in text, particularly padding markers and code-like patterns

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    picasso
    -0.60
     resourceCulture
    -0.59
    )++;
    -0.57
    CodedInputStream
    -0.56
    rmtree
    -0.55
    TextAppearance
    -0.54
     tỉ
    -0.52
    {{\
    -0.52
    UTERS
    -0.52
    Bergen
    -0.52
    POSITIVE LOGITS
     pad
    3.98
    Pad
    3.80
     Pad
    3.78
    pad
    3.72
     pads
    3.48
    pads
    3.33
     Pads
    3.33
     PAD
    2.91
    PAD
    2.88
    Pads
    2.80
    Activations Density 0.012%

    No Known Activations