© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6109
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    Negative Logits
     før
    -0.56
    glPopMatrix
    -0.55
    Gön
    -0.53
    hören
    -0.52
     Jü
    -0.52
    WebControls
    -0.51
     autant
    -0.50
     NSCoder
    -0.50
     appré
    -0.49
    Datuak
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.74
     ModelExpression
    0.57
     wikihow
    0.50
     ujednoznacz
    0.49
     most
    0.47
     the
    0.47
     hereinafter
    0.46
     inaczej
    0.46
     okuyayım
    0.45
    Neden
    0.45
    Activations Density 0.006%

    No Known Activations