© 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. 14532
    Prev
    Next
    INDEX
    Explanations

    technology and news

    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
    <bos>
    -0.56
     eventdata
    -0.50
    InputBorder
    -0.49
    FormTagHelper
    -0.47
    ClientSize
    -0.46
     a
    -0.45
    ///</
    -0.44
     processes
    -0.42
    orghini
    -0.42
     er
    -0.42
    POSITIVE LOGITS
    
    0.79
     pngtree
    0.67
     addObject
    0.67
     shipwreck
    0.62
     Malang
    0.62
    adpleegd
    0.62
     photolibrary
    0.61
     Gallen
    0.61
    +/**
    0.60
     vectorstock
    0.60
    Activations Density 0.084%

    No Known Activations