Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73803
    Prev
    Next
    INDEX
    Explanations

    code and technical language

    np_max-act-logits · 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
    .
    -0.59
     etc
    -0.43
    con
    -0.43
    !
    -0.43
     -
    -0.42
    last
    -0.40
     itself
    -0.40
    Revenir
    -0.39
     because
    -0.39
    ;
    -0.38
    POSITIVE LOGITS
    ")));
    
    0.87
    BeginContext
    0.85
    __":
    
    0.83
    ^(@)
    0.78
    ₁)
    0.75
    %");
    0.74
    %";
    0.74
    =$?
    0.74
    __':
    
    0.73
    ChildScrollView
    0.71
    Activations Density 0.041%

    No Known Activations