© 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. 0-CLT-HP
    7. 45568
    Prev
    Next
    INDEX
    Explanations

    upload

    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
     متعلقه
    -0.68
     comigo
    -0.60
     casó
    -0.60
     fråga
    -0.59
     of
    -0.57
    Enders
    -0.57
    guien
    -0.56
     situatie
    -0.56
     للمعارف
    -0.56
     conmigo
    -0.54
    POSITIVE LOGITS
     the
    1.55
     a
    1.27
     an
    1.09
     some
    1.04
     their
    1.00
     those
    0.95
     any
    0.94
     its
    0.89
     his
    0.85
     it
    0.85
    Activations Density 0.149%

    No Known Activations