© 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. 2-RES-MATRYOSHKA-DC
    7. 6157
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or place names

    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
     couche
    -0.48
    tritts
    -0.48
     Bevan
    -0.48
    assertIn
    -0.47
    恙
    -0.47
     Roman
    -0.47
    뤄
    -0.47
     Bex
    -0.46
     препратки
    -0.45
     sikkert
    -0.45
    POSITIVE LOGITS
    ville
    4.19
    VILLE
    3.94
    villes
    2.58
    Ville
    2.16
    vile
    1.96
    vill
    1.75
     Ville
    1.59
     ville
    1.56
    vil
    1.35
    VILL
    1.34
    Activations Density 0.009%

    No Known Activations