© 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. 1-CLT-HP
    7. 16156
    Prev
    Next
    INDEX
    Explanations

    technical and code 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
    Negative Logits
     chrétiens
    -0.67
     vostri
    -0.63
     varandra
    -0.62
    ,
    -0.61
     ägg
    -0.59
     médié
    -0.58
     fondament
    -0.57
     militaires
    -0.56
     imidlertid
    -0.55
     lisäksi
    -0.54
    POSITIVE LOGITS
    fillType
    0.54
    ತ್ತು
    0.54
    EndInit
    0.53
    ԁ
    0.52
    googleapis
    0.51
    hésitez
    0.50
    fatalError
    0.50
    rophi
    0.50
    multicolumn
    0.50
     Vac
    0.50
    Activations Density 1.142%

    No Known Activations