© 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. 7010
    Prev
    Next
    INDEX
    Explanations

    references to technical concepts and specific terminology related to mathematical, scientific, or medical 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
     idéia
    -1.38
     daß
    -1.30
     muß
    -1.18
     läßt
    -1.12
     Daß
    -1.03
     müßte
    -0.97
     biß
    -0.90
     mußten
    -0.87
     mußte
    -0.86
    faßt
    -0.86
    POSITIVE LOGITS
     microbiome
    1.12
     TikTok
    1.07
     onboarding
    1.05
     COVID
    1.02
    ️
    1.01
     curated
    0.99
     https
    0.98
     😅
    0.97
     🥲
    0.96
     LGBTQ
    0.96
    Activations Density 4.498%

    No Known Activations