© 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. 3471
    Prev
    Next
    INDEX
    Explanations

    common words "know", "get" and "that" as well as negations

    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
    ngdoc
    -0.76
    awtextra
    -0.75
    bootstrapcdn
    -0.74
     HasFactory
    -0.73
    WidgetItem
    -0.73
    styleType
    -0.72
     handleMessage
    -0.72
     typelib
    -0.71
     himself
    -0.71
    PendingIntent
    -0.68
    POSITIVE LOGITS
     ourselves
    1.57
     we
    1.12
     our
    1.02
     We
    0.94
    zimy
    0.90
     Our
    0.89
    我们是
    0.89
     будем
    0.88
    biamo
    0.87
     mamy
    0.85
    Activations Density 0.807%

    No Known Activations