© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5341
    Prev
    Next
    INDEX
    Explanations

    mentions of an individual's surname, particularly "Ger."

    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
    ligo
    -0.60
    TagMode
    -0.57
    wg
    -0.56
    sediaan
    -0.56
    ambilan
    -0.55
     ddelweddau
    -0.55
     fournisseurs
    -0.54
    Higgs
    -0.54
    ThemeOverlay
    -0.54
     Castel
    -0.54
    POSITIVE LOGITS
    ger
    3.70
     ger
    2.95
    GER
    2.92
    Ger
    2.77
     Ger
    2.61
    gers
    2.31
     GER
    2.27
    geri
    1.83
     germ
    1.77
    GERS
    1.73
    Activations Density 0.014%

    No Known Activations