© 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. 4-CLT-HP
    7. 1494
    Prev
    Next
    INDEX
    Explanations

    of

    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
    KommentareTeilen
    -0.81
    \{\\
    -0.77
    таратура
    -0.70
    ỡng
    -0.66
    !*\
    -0.64
     whereof
    -0.63
     craters
    -0.63
    setVerticalGroup
    -0.61
    WebVitals
    -0.61
     Infir
    -0.60
    POSITIVE LOGITS
     care
    0.60
     type
    0.52
     option
    0.51
     form
    0.50
     surgery
    0.50
     intervention
    0.48
     plan
    0.48
     procedure
    0.47
     exam
    0.46
     therapy
    0.46
    Activations Density 0.003%

    No Known Activations