© 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. 1-RES-MATRYOSHKA-DC
    7. 502
    Prev
    Next
    INDEX
    Explanations

    references to writing or creating data or 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
    LinkId
    -0.52
     Reveal
    -0.49
    awtextra
    -0.46
     Verge
    -0.46
    '}),
    -0.45
     ◄
    -0.44
     Issus
    -0.44
    beeren
    -0.44
    ffiche
    -0.43
    ionato
    -0.43
    POSITIVE LOGITS
     write
    3.89
     writing
    3.80
    write
    3.63
     Write
    3.52
     written
    3.45
    writing
    3.45
     Writing
    3.45
     wrote
    3.44
    Write
    3.39
    Writing
    3.39
    Activations Density 0.858%

    No Known Activations