© 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. 3464
    Prev
    Next
    INDEX
    Explanations

    discussions of the importance level or significance

    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
    ChildScrollView
    -0.85
    expandindo
    -0.82
     Савезне
    -0.82
     Chwiliwch
    -0.79
    wpdb
    -0.77
    RectangleBorder
    -0.75
     EClass
    -0.74
     Wikimedijinoj
    -0.73
    invokeLater
    -0.72
     BoxDecoration
    -0.72
    POSITIVE LOGITS
     significance
    2.63
     Significance
    2.41
     importance
    2.38
    Significance
    2.22
     Importance
    2.05
    importance
    2.02
    Importance
    1.89
     importancia
    1.70
     Bedeutung
    1.69
     relevance
    1.60
    Activations Density 0.025%

    No Known Activations