© 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. 3988
    Prev
    Next
    INDEX
    Explanations

    instructions or commands related to tracking, monitoring, or managing ongoing processes

    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
     held
    -0.82
     kept
    -0.71
     HELD
    -0.71
     Held
    -0.70
    kept
    -0.68
    Staying
    -0.65
    held
    -0.65
     Kept
    -0.65
    WithIOException
    -0.65
     Staying
    -0.64
    POSITIVE LOGITS
    Keep
    1.20
     Keep
    1.20
    keep
    0.90
     keep
    0.85
    KEEP
    0.73
     KEEP
    0.69
     continue
    0.65
    otheek
    0.62
    continue
    0.61
     Exacts
    0.59
    Activations Density 0.009%

    No Known Activations