© 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. 212
    Prev
    Next
    INDEX
    Explanations

    words associated with family and relationships

    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
    фю
    -0.57
    LEncoder
    -0.54
    ellate
    -0.54
    pageY
    -0.53
    adhé
    -0.52
     leerlingen
    -0.51
    imu
    -0.51
    requipa
    -0.51
     Counter
    -0.50
    chymal
    -0.50
    POSITIVE LOGITS
     family
    1.84
    family
    1.64
     families
    1.60
     FAMILY
    1.57
     Family
    1.55
    FAMILY
    1.52
    Family
    1.50
    Families
    1.48
     Families
    1.44
    families
    1.39
    Activations Density 1.910%

    No Known Activations