© 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. 6218
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Мексичка
    -0.67
    wnia
    -0.65
     GIG
    -0.64
     won
    -0.63
    shall
    -0.63
     judges
    -0.63
     the
    -0.63
    rítica
    -0.62
     runners
    -0.61
    TCC
    -0.61
    POSITIVE LOGITS
     himo
    0.54
     "..\..\..\
    0.48
     "..\..\
    0.44
    GEBURTSDATUM
    0.43
    SharedDtor
    0.42
     vizsg
    0.42
     transcur
    0.42
     stanovnika
    0.41
     respetar
    0.41
    windowFixed
    0.40
    Activations Density 0.293%

    No Known Activations