© 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
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77181
    Prev
    Next
    INDEX
    Explanations

    United States

    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
    "]));
    -0.97
    */;
    -0.77
    endphp
    -0.73
    })));
    -0.71
    Laws
    -0.70
    NameInMap
    -0.70
    NUMX
    -0.69
     تضيفلها
    -0.69
     Laws
    -0.69
     resourceCulture
    -0.69
    POSITIVE LOGITS
     U
    0.70
    U
    0.48
     American
    0.45
     domestic
    0.45
     US
    0.43
    Ugly
    0.36
     Domestic
    0.35
     primary
    0.35
     United
    0.35
    ूत
    0.35
    Activations Density 0.001%

    No Known Activations