© 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. 94445
    Prev
    Next
    INDEX
    Explanations

    political opinions

    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
     Majefty
    -0.66
     fevere
    -0.63
    berdayakan
    -0.63
     houſe
    -0.63
     Diſ
    -0.62
     ddelweddau
    -0.62
     Commencez
    -0.61
     Riproduzione
    -0.61
     quæ
    -0.60
    joba
    -0.60
    POSITIVE LOGITS
    <bos>
    0.91
    <()>
    0.56
     استنادى
    0.55
    RegressionTest
    0.52
    lamabad
    0.50
     Minister
    0.49
    Minister
    0.49
     Aviv
    0.48
    upol
    0.47
    hamcrest
    0.47
    Activations Density 0.100%

    No Known Activations