© 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. 6648
    Prev
    Next
    INDEX
    Explanations

    references to specific artworks, artists, or exhibitions, especially those involving the term "Lap" and museum or gallery names

    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
     Administrativna
    -0.87
    ArrowToggle
    -0.85
    httphttps
    -0.77
     Roskov
    -0.75
    kegaard
    -0.75
    openhauer
    -0.75
     resourceCulture
    -0.73
     ExecuteAsync
    -0.73
    parsedMessage
    -0.71
    Portale
    -0.70
    POSITIVE LOGITS
     Lap
    3.53
     lap
    3.47
    Lap
    3.39
     laps
    2.91
    lap
    2.73
    LAP
    2.20
     LAP
    2.16
    laps
    1.97
     lapar
    1.66
     lapse
    1.46
    Activations Density 0.011%

    No Known Activations