© 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. 2-RES-MATRYOSHKA-DC
    7. 6091
    Prev
    Next
    INDEX
    Explanations

    references to the concept of income, specifically identifying and emphasizing mentions of income and income-related terms

    oai_token-act-pair · gpt-4.1-nano
    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
    RegistryLite
    -0.65
     Bit
    -0.61
     AssemblyProduct
    -0.61
    enschappelijke
    -0.60
     @"/
    -0.59
    featureID
    -0.58
    awtextra
    -0.55
    WriteTagHelper
    -0.55
    AndroidJUnit
    -0.54
     μυ
    -0.54
    POSITIVE LOGITS
     income
    3.42
     Income
    3.25
    Income
    3.06
    income
    3.03
     INCOME
    3.03
     incomes
    2.39
     Einkommen
    1.91
     revenus
    1.73
    收入
    1.59
     ingresos
    1.59
    Activations Density 0.008%

    No Known Activations