© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1019
    Prev
    Next
    INDEX
    Explanations

    the word "therefore"

    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
    ValueStyle
    -0.68
    ing
    -0.68
     least
    -0.66
     Manne
    -0.64
    ']))
    -0.63
     man
    -0.63
    hol
    -0.62
     McKnight
    -0.62
    你也
    -0.61
    равда
    -0.60
    POSITIVE LOGITS
     therefore
    2.56
     Therefore
    2.31
    Therefore
    2.23
    therefore
    2.20
     therefor
    1.91
     donc
    1.70
     hence
    1.66
     derfor
    1.64
     portanto
    1.61
     därför
    1.57
    Activations Density 0.145%

    No Known Activations