© 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. 14841
    Prev
    Next
    INDEX
    Explanations

    references or mentions of a specific location, particularly the city of Holland

    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
    Moe
    -0.62
     automatiques
    -0.57
     Namens
    -0.56
     Raise
    -0.55
     Himo
    -0.55
     Coat
    -0.53
     Moe
    -0.52
    acă
    -0.52
    entz
    -0.52
    rosos
    -0.51
    POSITIVE LOGITS
     Holland
    3.25
    Holland
    3.23
     holland
    2.28
     HOLL
    2.25
     Holl
    1.97
    Holl
    1.70
    holland
    1.62
     holl
    0.99
    holl
    0.90
     Holanda
    0.65
    Activations Density 0.000%

    No Known Activations