© 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. 0-RES-MATRYOSHKA-DC
    7. 12148
    Prev
    Next
    INDEX
    Explanations

    references to geographic or administrative regions

    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
    ward
    -1.58
    wards
    -1.37
    WARD
    -1.02
    WARDS
    -0.92
    warded
    -0.78
     tfsi
    -0.59
     UnityEditor
    -0.59
    TagHelper
    -0.57
    rungsseite
    -0.56
    IContainer
    -0.55
    POSITIVE LOGITS
     wards
    2.11
     ward
    2.00
     fend
    0.68
    RuleContext
    0.64
    FormTagHelper
    0.57
     WARD
    0.57
    цездатний
    0.56
    ГЛА
    0.55
     مب
    0.53
     stave
    0.53
    Activations Density 0.000%

    No Known Activations