© 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. 14932
    Prev
    Next
    INDEX
    Explanations

    acetyl

    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
    s
    -0.60
    DispatchToProps
    -0.59
     Cuckoo
    -0.57
    o
    -0.56
    ed
    -0.55
    i
    -0.55
    e
    -0.55
     Munk
    -0.52
    MathML
    -0.52
    ing
    -0.52
    POSITIVE LOGITS
     électroniques
    0.59
     potuto
    0.59
     sauvages
    0.57
     numériques
    0.57
     ivelany
    0.55
     juridiques
    0.54
    Havolalar
    0.54
     privées
    0.54
     totalidad
    0.53
     skrevet
    0.53
    Activations Density 0.013%

    No Known Activations