© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42608
    Prev
    Next
    INDEX
    Explanations

    say believe

    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
     
    -0.81
    <eos>
    -0.81
     has
    -0.76
     is
    -0.75
     for
    -0.73
     can
    -0.72
     I
    -0.71
     be
    -0.69
     will
    -0.68
     in
    -0.68
    POSITIVE LOGITS
     Monfieur
    1.81
     Majefty
    1.80
     Efq
    1.78
     purpoſe
    1.77
     itſelf
    1.77
     myſelf
    1.77
    IntoConstraints
    1.70
     Jefus
    1.67
     themſelves
    1.62
     ſeveral
    1.62
    Activations Density 0.028%

    No Known Activations