© 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. 1-RES-MATRYOSHKA-DC
    7. 900
    Prev
    Next
    INDEX
    Explanations

    references to the word "word" in 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
     terms
    -0.55
    AntiForgeryToken
    -0.54
     ostavi
    -0.54
    Schmidt
    -0.47
    termin
    -0.46
     DialogInterface
    -0.46
    isuus
    -0.46
    Terms
    -0.45
    Gambas
    -0.45
     Misc
    -0.45
    POSITIVE LOGITS
     word
    4.66
    word
    4.22
    Word
    4.06
     Word
    3.94
     WORD
    3.78
    WORD
    3.59
     words
    3.34
    words
    3.20
     Words
    3.16
    Words
    3.08
    Activations Density 0.387%

    No Known Activations