© 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. 43363
    Prev
    Next
    INDEX
    Explanations

    Republican party / 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
     defaultstate
    -0.97
    NewUrlParser
    -0.91
     ***!
    -0.86
    ChildScrollView
    -0.86
    mybatisplus
    -0.84
     ་་
    -0.77
    WriteTagHelper
    -0.76
    ConstraintMaker
    -0.76
    ErrUnexpectedEOF
    -0.75
    SequentialGroup
    -0.75
    POSITIVE LOGITS
    s
    0.95
    ian
    0.88
    o
    0.87
    ia
    0.84
    an
    0.83
    ic
    0.82
    ed
    0.82
    ity
    0.79
    e
    0.78
    es
    0.77
    Activations Density 0.096%

    No Known Activations