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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2287
    Prev
    Next
    INDEX
    Explanations

    descriptions/explanations

    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
     the
    -1.44
     a
    -1.16
     an
    -1.08
     its
    -1.04
     his
    -0.92
     their
    -0.91
     both
    -0.86
     those
    -0.86
     our
    -0.85
     some
    -0.83
    POSITIVE LOGITS
     löyty
    0.76
     ouvertes
    0.73
     financières
    0.67
     situatie
    0.65
     casó
    0.63
     âgées
    0.63
     extérieurs
    0.62
     précédentes
    0.62
     délais
    0.61
     démocr
    0.61
    Activations Density 0.013%

    No Known Activations