© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 42261
    Prev
    Next
    INDEX
    Explanations

    nationalism

    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
     Efq
    -1.13
     myſelf
    -1.13
     itſelf
    -1.08
     greateſt
    -1.05
     himſelf
    -1.04
     purpoſe
    -1.02
    ſelves
    -1.00
     Majefty
    -1.00
    ⓧ
    -0.99
    ſelf
    -0.96
    POSITIVE LOGITS
    s
    0.83
    e
    0.75
     the
    0.72
     a
    0.68
     
    0.65
    es
    0.64
     of
    0.60
     (
    0.60
     "
    0.60
     to
    0.57
    Activations Density 0.100%

    No Known Activations