© 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. 0-CLT-HP
    7. 41356
    Prev
    Next
    INDEX
    Explanations

    piping

    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
     curved
    -0.56
     an
    -0.55
    bot
    -0.50
     th
    -0.49
     a
    -0.49
     i
    -0.49
    lijk
    -0.49
     studi
    -0.49
    st
    -0.48
     what
    -0.48
    POSITIVE LOGITS
     itſelf
    1.32
     myſelf
    1.16
     themſelves
    1.11
     himſelf
    1.08
     Theſe
    1.06
     Monfieur
    1.06
     Anſ
    1.02
     Houſe
    1.01
     Jefus
    0.98
     houſe
    0.97
    Activations Density 0.823%

    No Known Activations