© 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. 4-CLT-HP
    7. 1997
    Prev
    Next
    INDEX
    Explanations

    Parenthetical expressions and code

    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
    parsedMessage
    -0.74
    MLLoader
    -0.73
    ItemBackground
    -0.70
     NSCoder
    -0.61
    :✨
    -0.61
    AutoScaleMode
    -0.60
    bootstrapcdn
    -0.60
     jScrollPane
    -0.60
    ]]);
    -0.59
    bukkit
    -0.59
    POSITIVE LOGITS
     badly
    0.47
    unsplash
    0.44
    leski
    0.42
     kotlinx
    0.42
     poursu
    0.42
    umato
    0.41
    hoten
    0.41
    oxide
    0.40
    πέ
    0.40
    ñola
    0.40
    Activations Density 0.053%

    No Known Activations