© 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. 0-CLT-HP
    7. 1756
    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
    <bos>
    -1.66
     myſelf
    -0.90
     ainfi
    -0.86
     raiſ
    -0.85
    ']))
    -0.83
     ſhe
    -0.81
     ſtate
    -0.81
     itſelf
    -0.80
     Monfieur
    -0.79
     ſind
    -0.78
    POSITIVE LOGITS
     GR
    0.43
     Aw
    0.40
    PCL
    0.40
     Lu
    0.39
     BR
    0.39
    FLIP
    0.39
    ArgumentParser
    0.38
    HasOne
    0.38
     Cho
    0.38
     Nas
    0.38
    Activations Density 0.143%

    No Known Activations