© 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. 4428
    Prev
    Next
    INDEX
    Explanations

    instances of the word "engaged" or "engage" in context related to employment or activity during work

    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
    bootstrapcdn
    -0.74
     odeur
    -0.71
    aspectj
    -0.71
     referenties
    -0.69
    getValueAt
    -0.69
     sẻ
    -0.69
    Pud
    -0.69
     EconPapers
    -0.65
     Manipur
    -0.62
    multer
    -0.62
    POSITIVE LOGITS
     engage
    2.97
     engaged
    2.94
     engagement
    2.92
     engages
    2.83
     Engage
    2.63
    engaged
    2.61
     Engagement
    2.59
     engaging
    2.58
    Engagement
    2.53
    engage
    2.52
    Activations Density 0.029%

    No Known Activations