© 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. 5-CLT-HP
    7. 91303
    Prev
    Next
    INDEX
    Explanations

    fundamentally

    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
     many
    -0.64
     Many
    -0.62
    Banyak
    -0.61
     vieler
    -0.60
    recated
    -0.59
    Many
    -0.59
    httphttps
    -0.56
     often
    -0.55
    amaño
    -0.54
    сомо
    -0.54
    POSITIVE LOGITS
    RefNanny
    0.58
     stället
    0.56
    رشف
    0.51
     alemanes
    0.51
     küpe
    0.51
     varsa
    0.49
     quartzite
    0.48
     Enfin
    0.48
     habet
    0.48
    CrossRef
    0.48
    Activations Density 0.021%

    No Known Activations