© 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. 471
    Prev
    Next
    INDEX
    Explanations

    the phrase "the same" in various contexts

    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
    الحياه
    -0.71
     propOrder
    -0.67
    //
    -0.66
    [++
    -0.61
     different
    -0.60
     verschiedene
    -0.60
     ulike
    -0.59
     unterschied
    -0.59
    setupUi
    -0.58
     Various
    -0.57
    POSITIVE LOGITS
     same
    4.84
    same
    4.53
    Same
    4.34
     Same
    4.03
     SAME
    3.63
    SAME
    3.52
     mêmes
    2.98
     mismo
    2.95
     misma
    2.94
     mesma
    2.91
    Activations Density 0.676%

    No Known Activations