© 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. 0-CLT-HP
    7. 43790
    Prev
    Next
    INDEX
    Explanations

    production

    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
     producers
    -0.82
    fortawesome
    -0.58
     producer
    -0.56
     Producers
    -0.56
     marat
    -0.54
    TagHelper
    -0.52
    quels
    -0.51
    Shots
    -0.51
     bearer
    -0.50
     Minerva
    -0.49
    POSITIVE LOGITS
    EReference
    0.75
     EClass
    0.65
    Obrázky
    0.59
    tagext
    0.57
    writeFieldEnd
    0.56
    IUrlHelper
    0.56
    Vidite
    0.55
    Odour
    0.54
    kháu
    0.54
     <=",
    0.54
    Activations Density 1.517%

    No Known Activations