© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74862
    Prev
    Next
    INDEX
    Explanations

    technical language

    np_max-act-logits · 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
     EconPapers
    -0.85
     متعلقه
    -0.72
    Tikang
    -0.63
    principalTable
    -0.59
     bershka
    -0.59
    WithMany
    -0.58
     fuper
    -0.57
    новништво
    -0.57
    viewDidLoad
    -0.56
    amique
    -0.54
    POSITIVE LOGITS
     GlobalKey
    0.51
     know
    0.47
     FL
    0.45
     completely
    0.44
    SearchTree
    0.43
     really
    0.43
    Seeder
    0.43
    corrhi
    0.42
     known
    0.42
     precisely
    0.41
    Activations Density 0.000%

    No Known Activations