© 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. 93441
    Prev
    Next
    INDEX
    Explanations

    Why

    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
    :✨
    -0.83
    How
    -0.83
    adaptiveStyles
    -0.80
     itſelf
    -0.80
    tvguidetime
    -0.78
     myſelf
    -0.77
     How
    -0.76
     Cómo
    -0.75
     pleaſure
    -0.74
     Bagaimana
    -0.73
    POSITIVE LOGITS
     is
    1.20
     do
    1.18
     are
    1.16
     we
    1.02
     did
    1.01
     it
    0.98
     does
    0.98
     you
    0.98
     would
    0.98
     to
    0.97
    Activations Density 0.354%

    No Known Activations