© 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. 3117
    Prev
    Next
    INDEX
    Explanations

    references to the word "de," which indicates the neuron is identifying instances of the preposition or article "de" in various languages

    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
    脚注の使い方
    -0.84
     виправивши
    -0.84
     OST
    -0.73
    日閲覧
    -0.70
     Enix
    -0.70
    NameInMap
    -0.68
     समीक्षक
    -0.68
    utilisons
    -0.67
    ⓧ
    -0.66
    transQ
    -0.64
    POSITIVE LOGITS
     de
    1.60
     di
    1.02
     d
    0.79
     де
    0.75
     De
    0.72
    Géographie
    0.69
     də
    0.69
     <>",
    0.68
    De
    0.68
     pneumo
    0.67
    Activations Density 0.084%

    No Known Activations