© 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. 20-CLT-HP
    7. 71283
    Prev
    Next
    INDEX
    Explanations

    were

    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
    Negative Logits
     '\\;'
    -0.78
     AssemblyCompany
    -0.75
    setVerticalGroup
    -0.65
    fromnode
    -0.63
     otomatig
    -0.62
     يتيمه
    -0.62
     beginnetje
    -0.60
     chi̍t
    -0.58
    EndProject
    -0.57
     ivelany
    -0.57
    POSITIVE LOGITS
    참고
    0.60
     ag
    0.59
     gezet
    0.55
     above
    0.52
     fault
    0.52
    dessus
    0.51
     blame
    0.50
     uitz
    0.49
     muligt
    0.49
    )|^{
    0.49
    Activations Density 0.000%

    No Known Activations