© 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. 3225
    Prev
    Next
    INDEX
    Explanations

    references to significant geographical locations and infrastructure, especially roads, countries, and the world

    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
     prêtres
    -0.73
     étoient
    -0.72
    Personensuche
    -0.72
     enfans
    -0.71
     houſe
    -0.69
     Houſe
    -0.68
     pleaſure
    -0.68
     étoit
    -0.68
     avoient
    -0.66
     Efq
    -0.66
    POSITIVE LOGITS
     PublicKey
    0.54
     across
    0.49
    ...
    0.46
    ksi
    0.46
     ویکی‌آمباردا
    0.46
     Wh
    0.46
    AndEndTag
    0.45
     afield
    0.44
     ["",
    0.44
    ьаж
    0.44
    Activations Density 0.300%

    No Known Activations