© 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. 6488
    Prev
    Next
    INDEX
    Explanations

    references to the material glass

    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
    timbangan
    -0.62
     AttributeSet
    -0.60
     فريبيس
    -0.59
     kartą
    -0.58
    antaranya
    -0.58
    mayın
    -0.57
     choisissez
    -0.57
    ParallelGroup
    -0.55
    thma
    -0.54
     Shun
    -0.54
    POSITIVE LOGITS
    glass
    2.28
     Glass
    2.20
     glass
    2.19
    Glass
    2.16
     GLASS
    1.90
    GLASS
    1.73
     glas
    1.55
     Glas
    1.52
    Glas
    1.41
    glas
    1.34
    Activations Density 0.008%

    No Known Activations