© 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. 5-CLT-HP
    7. 2441
    Prev
    Next
    INDEX
    Explanations

    Monarchy

    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
     S
    -0.50
    ,
    -0.50
     E
    -0.49
    .
    -0.47
     K
    -0.47
     guess
    -0.47
     sit
    -0.47
     F
    -0.47
     M
    -0.46
     P
    -0.44
    POSITIVE LOGITS
     cérami
    0.81
    AndEndTag
    0.80
     quelcon
    0.80
     ainfi
    0.78
     fidé
    0.77
     définiti
    0.76
     destinées
    0.76
     financières
    0.75
    findpost
    0.75
     Anſ
    0.75
    Activations Density 0.051%

    No Known Activations