© 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. 78188
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    Autoritní
    -0.58
     مرئيه
    -0.57
     autorytatywna
    -0.56
    AccessorTable
    -0.56
    enumii
    -0.55
    localctx
    -0.54
     <<<<<<<<<<<<<<
    -0.53
     محفوظة
    -0.52
    ́c
    -0.52
    hooter
    -0.51
    POSITIVE LOGITS
     myſelf
    0.54
     whoſe
    0.52
    Geplaatst
    0.51
     Eſ
    0.48
     Efq
    0.48
     cauſe
    0.47
    saraba
    0.47
    uren
    0.46
    ineno
    0.44
     becauſe
    0.44
    Activations Density 0.003%

    No Known Activations