© 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. 0-CLT-HP
    7. 41295
    Prev
    Next
    INDEX
    Explanations

    government and legal proceedings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     legislature
    -1.38
     Legislature
    -1.16
     legislator
    -0.98
     Parliament
    -0.93
     parliament
    -0.88
     legislatures
    -0.85
     legislators
    -0.84
     legislative
    -0.80
     legislation
    -0.71
     LEGISL
    -0.71
    POSITIVE LOGITS
     pintadas
    0.73
     complètes
    0.69
     sólidos
    0.66
     défaite
    0.61
     pintados
    0.61
     hård
    0.60
     graphiques
    0.60
     planas
    0.59
     vanligt
    0.59
    AsUp
    0.59
    Activations Density 0.201%

    No Known Activations