© 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. 5018
    Prev
    Next
    INDEX
    Explanations

    information related to specific categories or classifications, particularly involving institutional names, geographic regions, and structured groupings

    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
    Rüyada
    -0.92
    SourceChecksum
    -0.81
    TagMode
    -0.79
     للاسماء
    -0.68
    windowFixed
    -0.67
     Paglinawan
    -0.67
     FontFamily
    -0.66
     TokenType
    -0.66
     createSprite
    -0.64
    featureID
    -0.63
    POSITIVE LOGITS
     CanadaChoose
    0.69
    ArgsConstructor
    0.61
     estimés
    0.60
     alike
    0.58
    ’
    0.55
     etc
    0.52
    enumi
    0.52
    Pyx
    0.50
    Others
    0.50
    出版年
    0.50
    Activations Density 4.633%

    No Known Activations