© 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. 3055
    Prev
    Next
    INDEX
    Explanations

    of

    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
     superiority
    -0.59
     bienfaits
    -0.55
     effectiveness
    -0.55
    ?’
    -0.55
     perception
    -0.54
    ?”
    -0.53
     argument
    -0.53
     usefulness
    -0.52
     valeur
    -0.51
     justification
    -0.51
    POSITIVE LOGITS
    Према
    0.77
    RenderAtEndOf
    0.66
     typelib
    0.66
    uxxxx
    0.62
     otomatig
    0.61
    SceneManagement
    0.61
    RegressionTest
    0.59
     Meksiku
    0.57
    enderror
    0.56
     تضيفلها
    0.55
    Activations Density 0.003%

    No Known Activations