© 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. 0-CLT-HP
    7. 42512
    Prev
    Next
    INDEX
    Explanations

    constitutions and countries

    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
     Constitution
    -0.89
    Constitution
    -0.77
     constitution
    -0.75
     Spain
    -0.70
    Spain
    -0.67
     Spaniard
    -0.66
     Spanish
    -0.65
     CONSTITUTION
    -0.65
    España
    -0.62
    Spanish
    -0.61
    POSITIVE LOGITS
    OGND
    0.74
    ry
    0.73
    onAttach
    0.65
     '\\;'
    0.63
    ResumeLayout
    0.60
     InputDecoration
    0.60
    AndEndTag
    0.58
    Gentle
    0.57
    UseVisualStyle
    0.57
    DoubleQuotes
    0.57
    Activations Density 0.142%

    No Known Activations