© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13812
    Prev
    Next
    INDEX
    Explanations

    references to Scottish parliamentary and local council constituencies

    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
     désolés
    -0.82
    AndEndTag
    -0.77
    /**
    -0.69
     EconPapers
    -0.67
     snippetHide
    -0.63
    findpost
    -0.63
    //
    -0.61
    Tikang
    -0.60
    featureID
    -0.60
    cardia
    -0.59
    POSITIVE LOGITS
    lack
    1.30
     kcal
    0.94
    buffers
    0.87
    subtitle
    0.85
    asan
    0.84
    Buffers
    0.83
     buffers
    0.82
    kcal
    0.79
    Debugger
    0.69
    sives
    0.66
    Activations Density 0.008%

    No Known Activations