© 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. 6-RES-MATRYOSHKA-DC
    7. 357
    Prev
    Next
    INDEX
    Explanations

    the word "but" and the immediately surrounding words

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Foxy
    -0.80
     Clarkson
    -0.80
    Suara
    -0.76
     gie
    -0.75
     Nemo
    -0.74
     Aire
    -0.73
     uric
    -0.73
     Foxy
    -0.73
     @}
    -0.72
    rinfo
    -0.72
    POSITIVE LOGITS
     But
    2.13
     but
    2.06
    But
    1.85
    but
    1.84
     BUT
    1.72
     pero
    1.59
    BUT
    1.48
     nhưng
    1.40
    但这
    1.33
    但
    1.30
    Activations Density 1.159%

    No Known Activations