© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14599
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    Not in Any Lists

    No Comments

    Negative Logits
     NDEBUG
    -0.58
     vôtre
    -0.55
    Domestic
    -0.54
     engraçadas
    -0.50
     brancas
    -0.48
    šanai
    -0.48
    umą
    -0.47
     ügy
    -0.47
     digelar
    -0.47
    SerializedSize
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.74
     Numerade
    0.70
     disambiguazione
    0.69
    ,:);
    0.60
     Smarty
    0.59
    存于互联网档案馆
    0.58
     виправивши
    0.58
     '\\;'
    0.56
     indisponible
    0.56
    inigte
    0.56
    Activations Density 2.955%

    No Known Activations