© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13440
    Prev
    Next
    INDEX
    Explanations

    evidence of a specific concept or event related to legal or institutional situations

    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
     realise
    -0.97
     realize
    -0.97
     الرياضيه
    -0.91
     realising
    -0.86
     realizing
    -0.83
    complexContent
    -0.81
     houſe
    -0.79
     autorytatywna
    -0.79
     ſeveral
    -0.77
     realisation
    -0.75
    POSITIVE LOGITS
     realized
    1.31
     realised
    1.06
     learned
    0.54
     found
    0.53
    ẠI
    0.46
    viv
    0.45
     figured
    0.45
     felt
    0.44
     wanted
    0.44
    出来
    0.43
    Activations Density 0.002%

    No Known Activations