© 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. 3366
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "WT," which likely stands for "wild type" in a scientific context

    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
     Swim
    -0.67
     PopupWindow
    -0.66
     Roskov
    -0.66
    torta
    -0.65
     Савезне
    -0.65
    orari
    -0.65
     Audiodateien
    -0.62
     Jamb
    -0.61
    toid
    -0.60
     Ceinture
    -0.60
    POSITIVE LOGITS
     WT
    2.30
    WT
    2.02
     wt
    1.30
    wt
    1.17
     Wt
    1.04
    Wt
    0.84
    WTS
    0.81
    MigrationBuilder
    0.67
     wild
    0.59
    wts
    0.58
    Activations Density 0.007%

    No Known Activations