© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1830
    Prev
    Next
    INDEX
    Explanations

    technical contexts

    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
    MENAFN
    -0.52
     intorno
    -0.51
     near
    -0.47
     Paglinawan
    -0.46
    يكب
    -0.46
    Geografía
    -0.44
    oirs
    -0.44
     is
    -0.44
     bords
    -0.43
    
    -0.43
    POSITIVE LOGITS
    IndentedString
    0.71
    HomeAsUpEnabled
    0.62
     autorytatywna
    0.59
    fjspx
    0.59
     الرياضيه
    0.53
     Abbé
    0.53
    :✨
    0.52
    viembre
    0.50
    Weiterlesen
    0.50
    Комплек
    0.50
    Activations Density 0.013%

    No Known Activations