© 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. 267
    Prev
    Next
    INDEX
    Explanations

    phrases with "want" or "wanted" followed by "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
    AddTagHelper
    -0.71
    uté
    -0.63
    CrossRef
    -0.63
     getRule
    -0.58
    йки
    -0.57
     faptul
    -0.57
    gewiesen
    -0.56
    tonsoft
    -0.55
     Kitts
    -0.54
    hip
    -0.54
    POSITIVE LOGITS
     want
    2.52
    want
    2.39
     wants
    2.34
    wants
    2.33
     wanted
    2.28
     Want
    2.27
     WANT
    2.23
     Wants
    2.23
     wanting
    2.09
    wanted
    2.05
    Activations Density 1.765%

    No Known Activations