© 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. 4-CLT-HP
    7. 748
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
     appunto
    -0.51
     egentlig
    -0.47
     Qualquer
    -0.46
     egentligen
    -0.45
     Tanto
    -0.45
    ”.
    -0.44
     beispielsweise
    -0.44
    ございました
    -0.43
     réellement
    -0.42
     respectively
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.95
    IndentedString
    0.90
     AssemblyCulture
    0.86
     PropertyChanged
    0.80
     ویکی‌پدی
    0.79
    AndEndTag
    0.79
     disambiguazione
    0.79
    GEBURTSDATUM
    0.77
    XmlAccessType
    0.77
    PhysRevD
    0.76
    Activations Density 0.002%

    No Known Activations