© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5739
    Prev
    Next
    INDEX
    Explanations

    references to URLs, online account verification, and related administrative terminology

    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
     isSet
    -0.56
    ovací
    -0.56
    ctive
    -0.54
     exigir
    -0.54
    uoja
    -0.52
     dimenti
    -0.52
    aluz
    -0.52
    тивні
    -0.52
    허
    -0.50
    enschein
    -0.49
    POSITIVE LOGITS
    MessageTagHelper
    0.79
    Искәрмәләр
    0.76
     }}-
    0.72
    ού
    0.68
    ρίου
    0.68
    ']):
    0.67
    ']){
    0.66
    =".$
    0.66
     }}\
    0.65
    tilor
    0.65
    Activations Density 0.092%

    No Known Activations