© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15798
    Prev
    Next
    INDEX
    Explanations

    words or terms related to specific chemical substances, biochemical processes, or scientific measurements

    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
    ########.
    -0.69
    webElementXpaths
    -0.58
    %)$
    -0.56
    RectangleBorder
    -0.55
    Geplaatst
    -0.54
     entanto
    -0.52
     Champlain
    -0.52
     Вікіпе
    -0.52
    MCA
    -0.52
     liitty
    -0.52
    POSITIVE LOGITS
    én
    0.80
    GraphicsUnit
    0.79
    日閲覧
    0.78
     smuggling
    0.77
     Randall
    0.73
    endphp
    0.71
     smuggled
    0.70
     EINVAL
    0.69
    Gotta
    0.69
     normative
    0.67
    Activations Density 0.084%

    No Known Activations