© 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. 2889
    Prev
    Next
    INDEX
    Explanations

    two

    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
     Roskov
    -0.81
    RegressionTest
    -0.75
     للمعارف
    -0.66
    Geplaatst
    -0.64
    readystatechange
    -0.61
     GeoNames
    -0.60
     learn
    -0.60
     protoimpl
    -0.60
    SpringBootTest
    -0.59
    utnik
    -0.56
    POSITIVE LOGITS
     useful
    0.63
     valuable
    0.57
     Useful
    0.56
    useful
    0.56
     new
    0.55
    pēc
    0.54
     things
    0.53
     élé
    0.53
     '+':
    0.52
     nouvelle
    0.51
    Activations Density 0.001%

    No Known Activations