© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4014
    Prev
    Next
    INDEX
    Explanations

    Republicans

    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
    themselves
    -1.05
     themselves
    -0.99
     their
    -0.79
    their
    -0.79
     Their
    -0.73
    Their
    -0.71
     THEIR
    -0.64
     kanilang
    -0.61
     الحره
    -0.60
    itself
    -0.60
    POSITIVE LOGITS
    PerformLayout
    0.78
    ectady
    0.57
    broek
    0.54
     malheur
    0.52
     grze
    0.51
    gdx
    0.50
    mobileqq
    0.50
    endphp
    0.50
     who
    0.50
    ｀)
    0.49
    Activations Density 0.002%

    No Known Activations