© 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. 11678
    Prev
    Next
    INDEX
    Explanations

    references to the process of viewing or examining (e.g., "voir")

    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
    ГЛА
    -0.77
    XmlAccessorType
    -0.63
    ModelAdmin
    -0.63
    ArgsConstructor
    -0.60
    MLLoader
    -0.60
    醐
    -0.60
     conci
    -0.59
    Бахар
    -0.59
    Gambas
    -0.54
    gameserver
    -0.54
    POSITIVE LOGITS
     PropTypes
    0.87
    izr
    0.77
     köl
    0.68
     austerity
    0.65
     Beech
    0.63
     giudi
    0.63
     pector
    0.61
    BoxShadow
    0.61
     unbounded
    0.60
    zyl
    0.57
    Activations Density 0.106%

    No Known Activations