© 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. 92016
    Prev
    Next
    INDEX
    Explanations

    Named entities

    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
     myſelf
    -1.74
     Efq
    -1.68
     itſelf
    -1.66
     purpoſe
    -1.59
     Monfieur
    -1.56
     pleaſure
    -1.55
     faſt
    -1.54
     Jefus
    -1.52
     Мексичка
    -1.50
     ―――――
    -1.48
    POSITIVE LOGITS
    .
    1.23
     
    1.15
    ,
    1.14
     (
    1.12
      
    0.96
     and
    0.94
    ↵
    0.91
     A
    0.90
    …
    0.88
     a
    0.87
    Activations Density 0.120%

    No Known Activations