© 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. 473
    Prev
    Next
    INDEX
    Explanations

    comparisons involving the word "than"

    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
    JoinColumn
    -0.58
    luss
    -0.49
    oj
    -0.48
    cupertino
    -0.48
    endgroup
    -0.47
     légale
    -0.47
     Cet
    -0.47
    tanleria
    -0.47
     therefore
    -0.47
    福
    -0.46
    POSITIVE LOGITS
     than
    4.06
     THAN
    3.59
    Than
    3.22
    than
    3.16
     Than
    3.11
     niż
    2.75
    THAN
    2.67
     än
    2.27
     decât
    2.11
     než
    2.09
    Activations Density 0.691%

    No Known Activations