© 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. 97664
    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
     (
    -1.99
    (
    -0.97
    ↵↵
    -0.90
    :
    -0.90
     [
    -0.88
      
    -0.86
     
    -0.84
     A
    -0.82
     –
    -0.77
     (_
    -0.77
    POSITIVE LOGITS
     myſelf
    1.66
     itſelf
    1.57
     Anſ
    1.49
     pleaſure
    1.45
     Monfieur
    1.45
     ſever
    1.41
     Reſ
    1.39
    ſelf
    1.38
     ſche
    1.38
     purpoſe
    1.38
    Activations Density 0.214%

    No Known Activations