© 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. 94727
    Prev
    Next
    INDEX
    Explanations

    Quantification/Measurement

    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
     enfans
    -1.13
     industriels
    -1.05
     mijne
    -0.96
     prêtres
    -0.93
     plufieurs
    -0.91
    ंदीखरीदारी
    -0.91
     Grecs
    -0.90
     nôtre
    -0.90
     giapp
    -0.88
     varandra
    -0.88
    POSITIVE LOGITS
    homonymie
    0.54
     temp
    0.51
     latter
    0.51
    ggak
    0.50
     mode
    0.50
     reac
    0.50
    __":
    0.50
     utility
    0.48
     ref
    0.47
     student
    0.47
    Activations Density 0.388%

    No Known Activations