© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 77013
    Prev
    Next
    INDEX
    Explanations

    Technical writing snippets

    np_max-act-logits · 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
     '\\;'
    -1.31
     EconPapers
    -1.28
    setVerticalGroup
    -1.18
    RenderAtEndOf
    -1.17
     kaarangay
    -1.15
     <>",
    -1.11
    ThroughAttribute
    -1.09
     autorytatywna
    -1.05
    IUrlHelper
    -1.04
     Bourgoin
    -1.03
    POSITIVE LOGITS
    .
    0.47
     n
    0.43
     i
    0.38
     pas
    0.37
     h
    0.36
    i
    0.36
     
    0.36
     for
    0.36
     m
    0.35
    1
    0.35
    Activations Density 0.002%

    No Known Activations