© 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. 3399
    Prev
    Next
    INDEX
    Explanations

    references to theatrical stages or performances

    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
     berta
    -0.50
     henvis
    -0.49
     refuer
    -0.48
     bassa
    -0.48
     ту
    -0.47
    umahan
    -0.45
     alemanes
    -0.45
     caza
    -0.44
    انگلیسی
    -0.44
    чник
    -0.44
    POSITIVE LOGITS
     podium
    1.20
     desk
    1.20
     shelves
    1.14
     desks
    1.12
     bench
    1.08
     Desk
    1.06
     shelf
    1.04
     pulpit
    1.01
     table
    0.98
    desk
    0.95
    Activations Density 0.631%

    No Known Activations