© 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. 95250
    Prev
    Next
    INDEX
    Explanations

    medical/technical procedures

    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
     myſelf
    -0.88
    onViewCreated
    -0.87
     Monfieur
    -0.85
    integrate
    -0.84
     integrate
    -0.81
     >=",
    -0.79
     itſelf
    -0.79
    NUMX
    -0.79
    ſelves
    -0.79
     TimeUnit
    -0.79
    POSITIVE LOGITS
    a
    0.66
    ing
    0.59
    e
    0.56
     
    0.54
    .
    0.51
    p
    0.50
    [
    0.49
    en
    0.48
    an
    0.48
    :
    0.48
    Activations Density 0.199%

    No Known Activations