© 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. 90879
    Prev
    Next
    INDEX
    Explanations

    scientific research papers

    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
     McE
    -0.49
    beginPath
    -0.46
    ponses
    -0.46
    تقاوى
    -0.45
    Искәрмәләр
    -0.45
     WaitForSeconds
    -0.45
     Drawable
    -0.44
     Metz
    -0.44
    rugada
    -0.44
    Enllaços
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.70
     autorytatywna
    0.59
    Gön
    0.57
     purpoſe
    0.56
     equatorial
    0.55
     wireType
    0.54
     vốn
    0.54
    ArgsConstructor
    0.53
     Pergamon
    0.52
     autoradio
    0.52
    Activations Density 0.309%

    No Known Activations