© 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. 5-CLT-HP
    7. 91921
    Prev
    Next
    INDEX
    Explanations

    repair/condition

    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
     تعدى
    -0.48
    няться
    -0.47
     kalah
    -0.45
    ANTLR
    -0.43
    гле
    -0.43
     것이다
    -0.42
     souci
    -0.41
    źnie
    -0.41
    BeNil
    -0.41
    umen
    -0.40
    POSITIVE LOGITS
    expandindo
    0.81
    Rohy
    0.77
    RegressionTest
    0.75
    Autoritní
    0.72
     nahilalakip
    0.71
    WebVitals
    0.69
     typelib
    0.69
    Identyfik
    0.69
     resourceCulture
    0.66
    GEBURTSDATUM
    0.66
    Activations Density 0.002%

    No Known Activations