© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1538
    Prev
    Next
    INDEX
    Explanations

    re

    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
    re
    -2.44
    Re
    -1.26
     re
    -1.23
     Re
    -1.22
    t
    -1.03
    RE
    -1.02
    n
    -1.02
    m
    -0.98
    d
    -0.97
    r
    -0.93
    POSITIVE LOGITS
    Autoritní
    1.41
     виправивши
    1.33
     estekak
    1.27
    OGND
    1.26
     незавершена
    1.19
     autorytatywna
    1.18
     дописавши
    1.17
    +#+#
    1.16
    contentLoaded
    1.15
     myſelf
    1.15
    Activations Density 0.190%

    No Known Activations