© 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. 7203
    Prev
    Next
    INDEX
    Explanations

    factual or informational content related to specific topics

    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
     working
    -1.48
     Working
    -1.42
    Working
    -1.42
     WORKING
    -1.39
    working
    -1.33
    WORKING
    -1.29
     Worked
    -1.16
    Worked
    -1.09
     worked
    -0.99
    worked
    -0.89
    POSITIVE LOGITS
     work
    1.45
    work
    1.16
    Work
    1.04
     Work
    1.00
     arbete
    0.82
     WORK
    0.81
     trabalho
    0.77
     munka
    0.72
    arbeit
    0.67
     arbejde
    0.67
    Activations Density 0.040%

    No Known Activations