© 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-CLT-HP
    7. 9663
    Prev
    Next
    INDEX
    Explanations

    Politics

    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
    SourceChecksum
    -0.92
     المعيارى
    -0.76
    BeginInit
    -0.71
    PerformLayout
    -0.70
    Personensuche
    -0.66
     nahilalakip
    -0.65
     terrestrial
    -0.63
    SuspendLayout
    -0.60
     NUKAT
    -0.60
     ComVisible
    -0.59
    POSITIVE LOGITS
     increase
    0.52
     creation
    0.49
     requirement
    0.49
     rise
    0.48
     operation
    0.48
     monster
    0.48
     man
    0.46
     gap
    0.45
     reduction
    0.45
     operations
    0.45
    Activations Density 0.025%

    No Known Activations