© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4065
    Prev
    Next
    INDEX
    Explanations

    research and the future

    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
    GEBURTSDATUM
    -1.10
    تقاوى
    -0.75
     Paglinawan
    -0.72
     ISNI
    -0.71
     kaarangay
    -0.69
    Hentet
    -0.69
     <>",
    -0.67
     referenties
    -0.65
    Geplaatst
    -0.64
    complexContent
    -0.63
    POSITIVE LOGITS
     where
    0.73
     donde
    0.53
     for
    0.53
     if
    0.52
    where
    0.50
     WHERE
    0.50
     success
    0.49
     whether
    0.49
     when
    0.48
     unless
    0.48
    Activations Density 0.003%

    No Known Activations