© 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. 0-RES-MATRYOSHKA-DC
    7. 15467
    Prev
    Next
    INDEX
    Explanations

    references to software or hardware components, specifically related to "ware" such as software packages or electronic components

    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
    token
    -0.52
     yew
    -0.52
    metingen
    -0.51
     Übersicht
    -0.48
     ميت
    -0.47
    syscall
    -0.47
     particulières
    -0.47
     groet
    -0.45
     réservés
    -0.44
    QMetaType
    -0.44
    POSITIVE LOGITS
    ware
    3.97
    WARE
    2.88
    Ware
    2.63
     ware
    2.11
    wares
    2.08
     Ware
    1.88
     WARE
    1.52
    ウェア
    1.09
    waren
    1.02
     متعلقه
    0.89
    Activations Density 0.000%

    No Known Activations