© 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. 2573
    Prev
    Next
    INDEX
    Explanations

    by

    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
    تقاوى
    -0.83
    PyExc
    -0.71
    Vidite
    -0.69
    RegressionTest
    -0.69
    ineno
    -0.67
    Tämä
    -0.66
    SequentialGroup
    -0.65
     disponibilités
    -0.65
    contentLoaded
    -0.64
    AndEndTag
    -0.64
    POSITIVE LOGITS
     increased
    0.79
     how
    0.73
     decreased
    0.71
     their
    0.69
     consistent
    0.69
     improved
    0.68
     statements
    0.59
     everything
    0.58
     continued
    0.57
     consistency
    0.57
    Activations Density 0.004%

    No Known Activations