© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12940
    Prev
    Next
    INDEX
    Explanations

    references to Pittsburgh

    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
     Stok
    -0.63
    FlatAppearance
    -0.57
     Darwin
    -0.54
     Alder
    -0.53
     Cairo
    -0.53
     Aba
    -0.53
    Abbas
    -0.53
     Cotton
    -0.52
    älä
    -0.52
     Abe
    -0.51
    POSITIVE LOGITS
     Pittsburgh
    2.97
    Pittsburgh
    2.66
     Pittsburg
    1.82
    BURGH
    1.33
     Steelers
    1.30
     Pitt
    1.00
    Pitt
    0.99
     Allegheny
    0.92
    tsburgh
    0.89
    rungsseite
    0.85
    Activations Density 0.001%

    No Known Activations