© 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. 6-RES-MATRYOSHKA-DC
    7. 868
    Prev
    Next
    INDEX
    Explanations

    Scandinavian names and places

    oai_token-act-pair · gemini-2.0-flash
    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
     transférez
    -0.62
     täv
    -0.62
    maier
    -0.61
    føring
    -0.60
     jorden
    -0.59
    borderSide
    -0.58
    ագրություններ
    -0.57
     måte
    -0.56
     ansik
    -0.56
     hemsida
    -0.56
    POSITIVE LOGITS
     Swedish
    0.92
     swedish
    0.92
     schwed
    0.91
    
    0.89
    skjaer
    0.85
    Swedish
    0.84
    Magnus
    0.82
     Nordic
    0.82
     norvég
    0.82
    Nordic
    0.82
    Activations Density 1.349%

    No Known Activations