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. 0-CLT-HP
    4. 44845
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
     whole
    -1.00
    whole
    -0.92
     entire
    -0.91
     Monfieur
    -0.82
     enfans
    -0.80
     itſelf
    -0.79
     ainfi
    -0.79
     Entire
    -0.77
     quæ
    -0.77
     WHOLE
    -0.76
    POSITIVE LOGITS
    ly
    0.59
    ROIT
    0.53
     sympy
    0.53
    ley
    0.50
     van
    0.50
     layui
    0.50
     Commencez
    0.47
     single
    0.47
     wake
    0.47
     resourceCulture
    0.46
    Activations Density 0.038%

    No Known Activations