© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14810
    Prev
    Next
    INDEX
    Explanations

    references to measurement units, specifically the term "FO" (likely short for "F" followed by numerical values), used in contexts involving measurement, requests, or specifications

    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
     fo
    -0.97
     Fo
    -0.63
    cupa
    -0.63
    abestanden
    -0.60
     foils
    -0.59
     محفوظة
    -0.58
    principalColumn
    -0.58
     nahilalakip
    -0.58
     transfieras
    -0.55
     foil
    -0.54
    POSITIVE LOGITS
    FO
    2.39
     FO
    1.12
    IFO
    0.67
     cherchés
    0.63
     FOB
    0.62
     Kalk
    0.61
    OGND
    0.59
    Seeder
    0.57
     Omer
    0.54
    Foreground
    0.53
    Activations Density 0.001%

    No Known Activations