© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13195
    Prev
    Next
    INDEX
    Explanations

    macro

    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
    s
    -0.55
    3
    -0.41
    <h3>
    -0.38
    9
    -0.37
      
    -0.35
     poli
    -0.34
    www
    -0.34
    1
    -0.34
    2
    -0.33
    https
    -0.33
    POSITIVE LOGITS
     ujednoznacz
    0.93
     &___
    0.93
    ReusableCell
    0.91
     defaultstate
    0.85
    expandindo
    0.83
     MenuView
    0.83
     itſelf
    0.82
     ModelExpression
    0.79
    IsContent
    0.78
     protoimpl
    0.77
    Activations Density 0.022%

    No Known Activations