© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3420
    Prev
    Next
    INDEX
    Explanations

    intensifiers

    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
     تضيفلها
    -0.74
     незавершена
    -0.68
    DoubleQuotes
    -0.61
    archiviato
    -0.60
    Хьажоргаш
    -0.59
    >');
    -0.57
    buttonShape
    -0.56
    }`).
    -0.56
     }}"></
    -0.56
     ComVisible
    -0.56
    POSITIVE LOGITS
    IntoConstraints
    0.48
     even
    0.48
     pronounced
    0.46
     dr
    0.46
    even
    0.46
     dro
    0.43
    utebol
    0.43
    parsedMessage
    0.43
     gar
    0.42
     gin
    0.42
    Activations Density 0.001%

    No Known Activations