© 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. 430
    Prev
    Next
    INDEX
    Explanations

    references to work or effort

    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
    Datuak
    -0.80
    piecze
    -0.63
    inalg
    -0.60
     bezeichneter
    -0.60
    CascadeType
    -0.59
    بوابة
    -0.57
    fromnode
    -0.54
    heiser
    -0.53
    elerik
    -0.52
    UrlResolution
    -0.52
    POSITIVE LOGITS
     work
    4.44
     Work
    4.06
    work
    4.03
    Work
    4.00
     WORK
    3.78
    WORK
    3.52
     works
    3.13
     worked
    3.11
     working
    2.92
    worked
    2.89
    Activations Density 0.615%

    No Known Activations