© 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. 790
    Prev
    Next
    INDEX
    Explanations

    the phrase "used to"

    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
     brewed
    -0.55
     trouvera
    -0.50
     memakan
    -0.50
    enderror
    -0.49
     organised
    -0.49
    __(/*!
    -0.48
     comiendo
    -0.48
    VIATIONS
    -0.48
     zoned
    -0.48
     boneca
    -0.47
    POSITIVE LOGITS
    用来
    0.95
     used
    0.93
     Used
    0.88
    用于
    0.87
     helps
    0.84
    Used
    0.84
     help
    0.81
     用于
    0.81
    Helps
    0.79
     helping
    0.77
    Activations Density 1.088%

    No Known Activations