© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3307
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lat" (likely as part of "latitude" or "latitudinal")

    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
    Negative Logits
     propOrder
    -0.94
     متعلقه
    -0.88
     CreateTagHelper
    -0.84
     referenties
    -0.80
    ThroughAttribute
    -0.77
    TextWatcher
    -0.73
     Taktlose
    -0.73
    adaptiveStyles
    -0.71
    geslacht
    -0.71
     resourceCulture
    -0.69
    POSITIVE LOGITS
     lat
    2.97
     Lat
    2.89
    Lat
    2.81
    lat
    2.61
    LAT
    2.34
     LAT
    2.33
     latitude
    1.40
    latitude
    1.39
     Latina
    1.38
     Latin
    1.37
    Activations Density 0.023%

    No Known Activations