© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4781
    Prev
    Next
    INDEX
    Explanations

    references to specific instances or examples

    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
    mybatisplus
    -0.91
    saraba
    -0.88
     even
    -0.66
     exemplu
    -0.65
    kadang
    -0.62
     etiam
    -0.61
    ברס
    -0.61
    dostęp
    -0.60
     itſelf
    -0.60
     ovunque
    -0.60
    POSITIVE LOGITS
     namely
    2.83
     Namely
    2.61
    namely
    2.50
     nämlich
    1.45
     nemlig
    1.39
     namelijk
    1.35
     viz
    1.27
     yaitu
    1.23
     yakni
    1.23
     ovvero
    1.23
    Activations Density 0.003%

    No Known Activations