© 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. 7282
    Prev
    Next
    INDEX
    Explanations

    references to awards and recognizing winners

    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
    Personensuche
    -0.64
     vostri
    -0.57
    thma
    -0.55
     loss
    -0.55
     lost
    -0.53
     Zil
    -0.53
     giây
    -0.53
     Schn
    -0.52
    rogly
    -0.52
    IGraphics
    -0.51
    POSITIVE LOGITS
     winner
    3.17
     winners
    3.16
    winner
    2.86
     Winner
    2.84
     Winners
    2.84
    winners
    2.70
    Winners
    2.67
    Winner
    2.63
     WINNER
    2.33
    WINNER
    2.09
    Activations Density 0.087%

    No Known Activations