© 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. 0-CLT-HP
    7. 40188
    Prev
    Next
    INDEX
    Explanations

    Louis

    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
     felt
    -1.16
     Louis
    -0.98
     rear
    -0.88
    ons
    -0.82
    Louis
    -0.81
    Felt
    -0.72
     Felt
    -0.66
    felt
    -0.65
     w
    -0.62
     louis
    -0.57
    POSITIVE LOGITS
     Efq
    1.03
     Monfieur
    1.01
     doubtnut
    0.95
     تانيه
    0.93
    PerformLayout
    0.92
    rungsseite
    0.92
     myſelf
    0.91
     autorytatywna
    0.90
     whoſe
    0.89
     $_"
    0.88
    Activations Density 0.330%

    No Known Activations