© 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. 2-RES-MATRYOSHKA-DC
    7. 3114
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wrote" 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
     spoken
    -0.88
     written
    -0.68
     taken
    -0.65
     Spoken
    -0.60
     Written
    -0.59
     quality
    -0.55
    written
    -0.55
    spoken
    -0.55
     driven
    -0.54
     Say
    -0.54
    POSITIVE LOGITS
     wrote
    1.63
     Wrote
    1.38
    wrote
    1.30
     schrieb
    1.13
     escribió
    1.02
     schreef
    0.99
    ⓧ
    0.96
    drew
    0.93
     escreveu
    0.93
     skrev
    0.92
    Activations Density 0.028%

    No Known Activations