© 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. 91047
    Prev
    Next
    INDEX
    Explanations

    gang

    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
    setVerticalGroup
    -0.55
     AsyncTask
    -0.48
    jspx
    -0.47
     asunder
    -0.45
     bassa
    -0.44
    tinger
    -0.44
    GeoNames
    -0.43
     OFDb
    -0.42
     surrounds
    -0.41
     rodea
    -0.41
    POSITIVE LOGITS
    出版年
    0.78
     nahilalakip
    0.74
    berdayakan
    0.74
     nakalista
    0.68
     onCreateView
    0.68
     BoxFit
    0.66
    principalTable
    0.61
    +#+#
    0.61
    Spoljašnje
    0.60
    consulté
    0.59
    Activations Density 0.004%

    No Known Activations