© 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. 20-CLT-HP
    7. 73123
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous text snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.69
    GeneratedCode
    -0.67
    ="@+
    -0.64
     Shakspeare
    -0.63
     Synagogue
    -0.62
    msgSender
    -0.57
     aVar
    -0.57
     Shaksp
    -0.56
     Synag
    -0.56
     DSC
    -0.56
    POSITIVE LOGITS
     until
    0.59
     Until
    0.55
    Until
    0.54
     Into
    0.54
     até
    0.53
    Into
    0.52
     into
    0.50
     jusqu
    0.49
     vorder
    0.49
    ToProps
    0.47
    Activations Density 0.007%

    No Known Activations