© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3411
    Prev
    Next
    INDEX
    Explanations

    the word "many"

    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
    Negative Logits
     paio
    -0.91
     handful
    -0.85
     enkele
    -0.85
     ilang
    -0.84
    couple
    -0.83
     aantal
    -0.81
    czegó
    -0.81
    PointSize
    -0.80
    NumOf
    -0.74
     couple
    -0.73
    POSITIVE LOGITS
     many
    1.35
    many
    1.30
     Many
    1.27
    Many
    1.26
    MANY
    1.20
     MANY
    1.18
     muchas
    0.95
     muchos
    0.90
     Muchas
    0.83
     vielen
    0.82
    Activations Density 0.052%

    No Known Activations