© 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. 1-RES-MATRYOSHKA-DC
    7. 1192
    Prev
    Next
    INDEX
    Explanations

    references to electoral processes, including elections, campaigns, voters, and political figures involved in voting and election activities

    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
     maîtrise
    -0.51
     convenio
    -0.47
    жено
    -0.46
    établissement
    -0.44
    anzas
    -0.44
    odb
    -0.43
    ழ்
    -0.42
    ensee
    -0.42
     коэффици
    -0.42
    nessed
    -0.42
    POSITIVE LOGITS
     election
    2.80
     Election
    2.67
     elections
    2.52
     vote
    2.48
    Election
    2.48
     Elections
    2.41
     voter
    2.36
    election
    2.34
     ELECTION
    2.34
     voting
    2.33
    Activations Density 0.685%

    No Known Activations