© 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. 1
    Prev
    Next
    INDEX
    Explanations

    instances of the word "were" in the text

    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
     purpoſe
    -0.96
     ſtate
    -0.93
     houſe
    -0.91
     ſever
    -0.88
     Chriftian
    -0.86
     poffible
    -0.85
     pleaſure
    -0.85
     uſed
    -0.83
     fevere
    -0.83
     raiſ
    -0.83
    POSITIVE LOGITS
     is
    2.55
     are
    2.50
     were
    2.27
     was
    2.16
     WERE
    1.57
     be
    1.55
     ARE
    1.55
     has
    1.49
    were
    1.49
     Are
    1.47
    Activations Density 8.635%

    No Known Activations