© 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. 1-RES-MATRYOSHKA-DC
    7. 257
    Prev
    Next
    INDEX
    Explanations

    the overarching concept of mathematical bounds, limits, or constraints

    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
    AsUp
    -0.74
    ReusableCell
    -0.59
    ViewFeatures
    -0.58
    SaveChangesAsync
    -0.57
     مُعرِّف
    -0.56
     createState
    -0.55
    DispatchToProps
    -0.50
    يميديا
    -0.50
     pagare
    -0.49
     وصلة
    -0.49
    POSITIVE LOGITS
     limit
    3.98
     Limit
    3.72
    limit
    3.67
     limits
    3.67
     limited
    3.66
    Limit
    3.52
    limited
    3.45
     LIMIT
    3.36
     Limits
    3.33
     Limited
    3.31
    Activations Density 0.509%

    No Known Activations