© 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. 38532
    Prev
    Next
    INDEX
    Explanations

    decrease

    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
    Decre
    -0.88
    decre
    -0.84
     Decreased
    -0.81
     decreased
    -0.81
     diminished
    -0.78
    decrease
    -0.77
     shortened
    -0.74
     decreases
    -0.73
     vectorielles
    -0.73
     decreasing
    -0.72
    POSITIVE LOGITS
    ed
    0.82
    ing
    0.81
    en
    0.59
     the
    0.56
     to
    0.54
     للمعارف
    0.52
    ie
    0.51
    ik
    0.50
    er
    0.49
    ening
    0.48
    Activations Density 0.033%

    No Known Activations