© 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. 3362
    Prev
    Next
    INDEX
    Explanations

    the verb "blow" followed by other words; it seems to be sensitive to idioms

    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
     Normdatei
    -0.50
    Glitch
    -0.49
    秩序
    -0.49
    قط
    -0.49
    Ferro
    -0.49
     escur
    -0.48
     druž
    -0.48
     rette
    -0.46
     companhia
    -0.46
     (
    -0.45
    POSITIVE LOGITS
     blow
    3.17
     blown
    3.05
     blowing
    3.03
     blew
    2.91
     Blow
    2.89
     blows
    2.88
    blow
    2.86
    Blow
    2.75
    blowing
    2.47
    blown
    2.38
    Activations Density 0.041%

    No Known Activations