© 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. 43290
    Prev
    Next
    INDEX
    Explanations

    written

    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
     written
    -2.33
     Written
    -1.80
    written
    -1.73
    Written
    -1.58
     WRITTEN
    -1.56
     spoken
    -1.24
     escrito
    -1.23
     printed
    -1.20
     écrite
    -1.14
     scritto
    -1.12
    POSITIVE LOGITS
    ]));
    
    0.67
    thood
    0.63
    +#+
    0.62
     }}"></
    0.60
    /
    
    0.60
    ]))
    
    0.60
    )}</
    0.59
    PRNewswire
    0.59
    EDEFAULT
    0.58
    "]);
    
    0.57
    Activations Density 0.392%

    No Known Activations