© 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. 4583
    Prev
    Next
    INDEX
    Explanations

    blog/article snippets

    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
     nahilalakip
    -0.65
    PerformLayout
    -0.62
    WireFormatLite
    -0.62
    RegressionTest
    -0.59
    
    -0.57
     الحره
    -0.56
     bisect
    -0.56
     دیکھیے
    -0.53
    either
    -0.53
    Either
    -0.52
    POSITIVE LOGITS
     of
    0.79
     must
    0.58
     our
    0.58
    URLException
    0.50
     Past
    0.48
     recently
    0.47
     we
    0.47
    stretchr
    0.47
    SizeF
    0.47
    řevě
    0.47
    Activations Density 0.001%

    No Known Activations