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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 76
    Prev
    Next
    INDEX
    Explanations

    at

    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
     institutions
    -0.63
     an
    -0.61
     a
    -0.61
     multiple
    -0.57
    verwijspagina
    -0.56
     one
    -0.56
     universities
    -0.53
     another
    -0.53
     partners
    -0.53
     large
    -0.52
    POSITIVE LOGITS
     المعيارى
    0.65
    })*/
    0.63
    });*/
    0.62
    writeFieldEnd
    0.60
    __":
    
    0.60
    CompilerServices
    0.57
     venons
    0.57
    };*/
    0.57
    ruptedException
    0.55
    ″]
    0.55
    Activations Density 0.001%

    No Known Activations