© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4817
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific code markers used for annotations or comments in source code

    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
     markers
    -0.85
     marker
    -0.74
     Markers
    -0.72
     labelled
    -0.70
    Markers
    -0.69
    markers
    -0.68
     labeled
    -0.67
     marked
    -0.66
    labelled
    -0.63
     Marked
    -0.63
    POSITIVE LOGITS
     Mark
    2.17
    Mark
    2.09
    mark
    2.05
     mark
    1.68
    MARK
    1.52
     MARK
    1.25
    マーク
    0.80
     マーク
    0.80
    marck
    0.77
    ViewInit
    0.71
    Activations Density 0.008%

    No Known Activations