© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15815
    Prev
    Next
    INDEX
    Explanations

    Patel

    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
     Patel
    -0.90
     canonical
    -0.51
     of
    -0.50
    ooga
    -0.49
    iti
    -0.49
     storici
    -0.44
    inal
    -0.44
    ical
    -0.44
    ial
    -0.43
    ac
    -0.43
    POSITIVE LOGITS
    IsMutable
    0.88
     AppColors
    0.70
     Савезне
    0.68
     onCreateView
    0.67
    currentColor
    0.66
    twimg
    0.66
    Personensuche
    0.66
     تانيه
    0.64
    validators
    0.64
     EnglishChoose
    0.63
    Activations Density 0.042%

    No Known Activations