© 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. 6701
    Prev
    Next
    INDEX
    Explanations

    references to the process of performing work or tasks

    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
     work
    -1.20
    work
    -1.01
     travaux
    -0.91
    Work
    -0.90
     Work
    -0.86
     WORK
    -0.84
     obra
    -0.81
    WORK
    -0.72
     arbete
    -0.70
     Werke
    -0.68
    POSITIVE LOGITS
     working
    2.78
    Working
    2.64
     Working
    2.63
     WORKING
    2.45
    working
    2.44
    WORKING
    2.16
     functioning
    1.16
     trabajando
    1.13
     operating
    1.04
     trabalhando
    1.03
    Activations Density 0.168%

    No Known Activations