© 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. 960
    Prev
    Next
    INDEX
    Explanations

    the word "government"

    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
     Dinah
    -0.65
    Barcode
    -0.63
     Nes
    -0.59
    Xna
    -0.59
    𝒌
    -0.57
    cards
    -0.56
    Cards
    -0.56
    Zac
    -0.56
     unknownFields
    -0.55
    trane
    -0.55
    POSITIVE LOGITS
     Government
    2.11
    Government
    2.05
     government
    1.93
     GOVERNMENT
    1.84
    GOVERNMENT
    1.80
    government
    1.77
     Govt
    1.74
    Govt
    1.63
     govt
    1.63
    vernment
    1.60
    Activations Density 0.180%

    No Known Activations