© 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. 5-CLT-HP
    7. 93966
    Prev
    Next
    INDEX
    Explanations

    learning and documentation

    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
     their
    -1.05
     they
    -0.82
     his
    -0.69
     the
    -0.65
     THEIR
    -0.63
     them
    -0.61
    their
    -0.60
     mereka
    -0.57
     its
    -0.53
     men
    -0.52
    POSITIVE LOGITS
     larmes
    0.70
     épaules
    0.68
     enfans
    0.66
     prochaines
    0.66
     âmes
    0.64
     précédents
    0.64
     prossima
    0.63
     précédentes
    0.62
     convaincre
    0.61
     venons
    0.60
    Activations Density 0.000%

    No Known Activations