© 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. 1-CLT-HP
    7. 9443
    Prev
    Next
    INDEX
    Explanations

    to

    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
    MessageOf
    -1.21
    IntoConstraints
    -1.10
    ValueStyle
    -1.06
     Paglinawan
    -0.95
    richTextPanel
    -0.95
    GEBURTSDATUM
    -0.95
    ⓧ
    -0.93
    DockStyle
    -0.92
    SequentialGroup
    -0.91
     архивлан
    -0.90
    POSITIVE LOGITS
     us
    0.66
     you
    0.59
     everyone
    0.59
     all
    0.57
     be
    0.52
     them
    0.52
     keep
    0.50
     produce
    0.50
     give
    0.50
     everybody
    0.48
    Activations Density 0.200%

    No Known Activations