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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97747
    Prev
    Next
    INDEX
    Explanations

    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
    Personensuche
    -0.98
    ValueStyle
    -0.96
     سكانية
    -0.94
     Мексичка
    -0.92
    Personendaten
    -0.90
     uſ
    -0.90
     auffi
    -0.88
     Monfieur
    -0.86
     reaſon
    -0.85
    enderror
    -0.85
    POSITIVE LOGITS
     “
    0.51
     s
    0.51
     and
    0.51
      
    0.48
     sa
    0.47
     spe
    0.47
     
    0.47
     x
    0.47
     (
    0.46
     pe
    0.46
    Activations Density 0.332%

    No Known Activations