© 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. 1070
    Prev
    Next
    INDEX
    Explanations

    the word "want"

    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
     REQUEST
    -0.81
     requests
    -0.81
     request
    -0.79
     requ
    -0.78
     Seeking
    -0.78
     Request
    -0.77
    REQUEST
    -0.77
     seeking
    -0.73
     requested
    -0.73
     Bates
    -0.70
    POSITIVE LOGITS
     want
    1.88
    want
    1.70
     Want
    1.56
     WANT
    1.55
    Want
    1.46
     wants
    1.41
    WANT
    1.37
     Wants
    1.24
    wants
    1.16
     wanted
    1.11
    Activations Density 0.064%

    No Known Activations