© 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. 1-CLT-HP
    7. 12976
    Prev
    Next
    INDEX
    Explanations

    lied

    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
    lied
    -1.48
     CLA
    -0.97
    CLA
    -0.81
    maz
    -0.61
     demais
    -0.49
    康
    -0.46
     Rück
    -0.46
    PictureBox
    -0.43
     pot
    -0.42
    cott
    -0.42
    POSITIVE LOGITS
     itſelf
    0.98
     Monfieur
    0.96
     myſelf
    0.94
     fevere
    0.92
     Majefty
    0.91
     chofe
    0.90
     Jefus
    0.80
    ſelves
    0.80
     purpoſe
    0.79
     typelib
    0.79
    Activations Density 0.019%

    No Known Activations