© 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. 0-RES-MATRYOSHKA-DC
    7. 12987
    Prev
    Next
    INDEX
    Explanations

    references to ancient civilizations and historical artifacts related to hygiene and sanitary inventions

    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
    spraak
    -0.54
    talk
    -0.44
     sit
    -0.44
     falar
    -0.43
    kunta
    -0.40
    ify
    -0.39
    latt
    -0.39
    imet
    -0.39
     Schluss
    -0.39
     år
    -0.39
    POSITIVE LOGITS
     Germans
    1.76
     Turks
    1.52
     Egyptians
    1.49
     Russians
    1.43
     Greeks
    1.38
     Danes
    1.34
     Spaniards
    1.32
     Swedes
    1.29
     Koreans
    1.27
     Italians
    1.25
    Activations Density 0.007%

    No Known Activations