© 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. 6-RES-MATRYOSHKA-DC
    7. 1383
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a conditional statement

    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
     kenne
    -0.56
    lendir
    -0.52
     <<<<<<<<<<<<<<
    -0.51
    VIAF
    -0.50
    MessageTagHelper
    -0.49
     cív
    -0.49
    apnews
    -0.48
    <!--[
    -0.47
    ainville
    -0.47
     lenker
    -0.47
    POSITIVE LOGITS
     moindre
    0.77
    的话
    0.75
     or
    0.72
     yoksa
    0.72
     perchance
    0.69
    的話
    0.68
    didSet
    0.66
     esetén
    0.66
    SpringBootTest
    0.65
    Tikang
    0.65
    Activations Density 2.058%

    No Known Activations