© 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. 5-CLT-HP
    7. 94256
    Prev
    Next
    INDEX
    Explanations

    React, Controller application code

    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
     IBOutlet
    -0.56
    bleau
    -0.54
     RFI
    -0.52
    TypedDataSet
    -0.51
     mío
    -0.50
    Kaieteur
    -0.49
     discontinuity
    -0.48
     IEnumerator
    -0.47
     externs
    -0.47
     ioutil
    -0.47
    POSITIVE LOGITS
    تقاوى
    0.57
     that
    0.57
     was
    0.56
     sánh
    0.56
    founded
    0.54
    Портали
    0.54
    Архівовано
    0.53
    was
    0.52
    ferred
    0.52
    wrote
    0.52
    Activations Density 0.000%

    No Known Activations