© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 758
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated terms from computer code, historical names, medical terms, measurement and probabilities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.00
     lenker
    -0.96
     getItemId
    -0.92
    modelBuilder
    -0.90
    HasAnnotation
    -0.88
     CSM
    -0.86
     NLA
    -0.85
    extAlignment
    -0.85
    Tembelea
    -0.85
    mazoo
    -0.84
    POSITIVE LOGITS
    c
    1.05
    ics
    1.02
    lec
    1.02
    tic
    1.00
    poc
    0.98
    ac
    0.96
     Moc
    0.96
    Buc
    0.96
    moc
    0.95
    FIC
    0.95
    Activations Density 2.815%

    No Known Activations