© 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. 5-CLT-HP
    4. 92545
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    djangoproject
    -0.58
     createState
    -0.54
    ]%
    -0.50
     suffers
    -0.49
    ]=="
    -0.48
    VIRONMENT
    -0.48
    '],
    
    -0.47
     {},
    
    -0.47
    reportWebVitals
    -0.47
    }`).
    -0.47
    POSITIVE LOGITS
     There
    0.77
    there
    0.71
    There
    0.70
     Here
    0.70
     We
    0.70
     You
    0.70
    You
    0.66
     there
    0.66
     if
    0.65
    We
    0.65
    Activations Density 0.002%

    No Known Activations