© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15774
    Prev
    Next
    INDEX
    Explanations

    references to the chemical element "de" (deuterium) and its various contexts

    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
     DE
    -1.01
     De
    -0.86
    DE
    -0.77
    De
    -0.75
     Де
    -0.63
    DEO
    -0.60
     gì
    -0.59
     Deb
    -0.55
    teness
    -0.53
    d
    -0.53
    POSITIVE LOGITS
    de
    0.66
    NUMX
    0.65
    DidLoad
    0.64
    Xna
    0.62
     tyle
    0.62
     secours
    0.61
    ualaikum
    0.58
     cesse
    0.57
    ztály
    0.56
    fficio
    0.55
    Activations Density 0.004%

    No Known Activations