© 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. 3130
    Prev
    Next
    INDEX
    Explanations

    references to specific sectors or fields, particularly the "sector" sector

    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
     merchan
    -0.59
     Mercan
    -0.56
     mercan
    -0.56
    venger
    -0.54
     Gret
    -0.52
    Jenn
    -0.51
    ]--;
    -0.50
    userManager
    -0.49
    dealer
    -0.49
     delen
    -0.49
    POSITIVE LOGITS
     sector
    3.23
     Sector
    3.19
     SECTOR
    3.09
    sector
    3.03
    Sector
    2.98
     sectors
    2.91
     Sectors
    2.72
    SECTOR
    2.59
    sectors
    2.53
     sektor
    2.25
    Activations Density 0.003%

    No Known Activations