© 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. 6-RES-MATRYOSHKA-DC
    7. 354
    Prev
    Next
    INDEX
    Explanations

    the word "said"

    oai_token-act-pair · gemini-2.0-flash
    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
     Staub
    -0.73
     Morty
    -0.65
    FXMLLoader
    -0.64
    )|^{
    -0.63
    `]
    -0.63
    Gera
    -0.63
    /');
    -0.62
    もら
    -0.60
     Gesch
    -0.60
     resultList
    -0.60
    POSITIVE LOGITS
     said
    1.85
     Says
    1.77
     says
    1.77
    said
    1.68
    says
    1.68
    Says
    1.67
     SAYS
    1.67
     SAY
    1.65
     say
    1.60
     Saying
    1.60
    Activations Density 0.606%

    No Known Activations