© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29539
    Prev
    Next
    INDEX
    Explanations

    the word "wanted" or "want" in various tenses.

    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
    encode
    -0.61
     wish
    -0.57
     Gericht
    -0.56
     saites
    -0.56
    grès
    -0.56
     Erskine
    -0.55
     Rosa
    -0.55
     gustaría
    -0.54
     FirstName
    -0.54
     creek
    -0.53
    POSITIVE LOGITS
    AccessorTable
    0.80
    FormTagHelper
    0.72
     kaynağından
    0.70
     "','
    0.68
     bougies
    0.64
    ,:,
    0.63
     esternos
    0.63
    ')['
    0.63
    مصادر
    0.62
    maxcdn
    0.61
    Activations Density 0.022%

    No Known Activations