© 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. 1-RES-MATRYOSHKA-DC
    7. 881
    Prev
    Next
    INDEX
    Explanations

    comparisons of numerical values, specifically identifying superlative terms related to "greatest" or "highest."

    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
    more
    -0.79
     more
    -0.76
    near
    -0.73
     near
    -0.69
     Most
    -0.69
    Most
    -0.68
     most
    -0.68
     More
    -0.67
    Near
    -0.65
     much
    -0.63
    POSITIVE LOGITS
     highest
    2.81
     largest
    2.81
    highest
    2.69
     longest
    2.67
     smallest
    2.66
    largest
    2.63
     widest
    2.56
     lowest
    2.55
     Highest
    2.48
     tallest
    2.48
    Activations Density 0.131%

    No Known Activations