© 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. 5-CLT-HP
    7. 4988
    Prev
    Next
    INDEX
    Explanations

    from

    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
     genoux
    -0.67
     päivä
    -0.59
     rêves
    -0.54
     lèvres
    -0.53
     histoires
    -0.52
     démocr
    -0.51
     supplémentaires
    -0.51
     nuages
    -0.50
     complètes
    -0.50
     quelcon
    -0.49
    POSITIVE LOGITS
     disambiguazione
    0.89
    expandindo
    0.88
    DoubleQuotes
    0.83
     NSCoder
    0.83
     متعلقه
    0.80
    تقاوى
    0.79
     الحره
    0.78
     Normdatei
    0.78
     estekak
    0.78
    uxxxx
    0.73
    Activations Density 0.001%

    No Known Activations