© 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. 7366
    Prev
    Next
    INDEX
    Explanations

    descriptions of chemical formulations and compositions

    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
    VersionUID
    -0.67
    WindowConstants
    -0.61
    BorderFactory
    -0.58
     withRouter
    -0.54
    請繼續往下閱讀
    -0.54
    Datuak
    -0.53
    ConstraintMaker
    -0.52
    ultati
    -0.51
     Rhapsody
    -0.51
    alism
    -0.50
    POSITIVE LOGITS
    ärä
    0.54
     wt
    0.54
     molar
    0.54
     weight
    0.52
     الترك
    0.52
    Produzione
    0.52
    weight
    0.51
    الحياه
    0.51
     구성
    0.49
    beyond
    0.49
    Activations Density 0.657%

    No Known Activations