© 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. 39874
    Prev
    Next
    INDEX
    Explanations

    vole

    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
     controlling
    -0.59
    ronom
    -0.55
      
    -0.50
     frequent
    -0.49
    eston
    -0.49
    yah
    -0.49
    petitive
    -0.48
     “
    -0.47
    reven
    -0.47
     fre
    -0.47
    POSITIVE LOGITS
     myſelf
    0.93
     ―――――
    0.86
     Monfieur
    0.86
    parsedMessage
    0.81
     Diſ
    0.77
     Theſe
    0.76
     themſelves
    0.76
     itſelf
    0.75
     Проци
    0.75
     Shakspeare
    0.75
    Activations Density 0.341%

    No Known Activations