© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 95151
    Prev
    Next
    INDEX
    Explanations

    prank

    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
    )");
    
    -1.05
    ']))
    
    -0.97
    InSection
    -0.96
    '))
    
    -0.91
    "):
    
    -0.89
     propOrder
    -0.89
    ")));
    
    -0.87
    )";
    
    -0.85
     cherchés
    -0.84
     Мексичка
    -0.84
    POSITIVE LOGITS
    land
    0.59
    ling
    0.58
    ly
    0.57
    ings
    0.54
    iness
    0.54
    ING
    0.52
    ial
    0.52
    tain
    0.52
    ni
    0.51
    amiento
    0.51
    Activations Density 1.687%

    No Known Activations