© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94942
    Prev
    Next
    INDEX
    Explanations

    government/legal matters

    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
     wikipagina
    -0.56
    DeleteBehavior
    -0.55
    imba
    -0.54
    obus
    -0.50
    medriver
    -0.49
    mography
    -0.49
     jLabel
    -0.47
    HttpConnection
    -0.46
     veuillez
    -0.46
     keduanya
    -0.45
    POSITIVE LOGITS
     schemes
    0.59
    schemes
    0.56
     laws
    0.56
     farms
    0.56
    OGND
    0.54
    Distribuzione
    0.54
    ficulties
    0.51
    Personendaten
    0.51
     Schemes
    0.50
    Décès
    0.50
    Activations Density 0.001%

    No Known Activations