© 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. 1-CLT-HP
    7. 13712
    Prev
    Next
    INDEX
    Explanations

    Week or Revolution

    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
     BoxDecoration
    -0.51
     CHtml
    -0.40
     verk
    -0.38
    xhr
    -0.36
     Week
    -0.36
     %>%
    -0.36
    revolution
    -0.35
     næ
    -0.35
    Jedis
    -0.35
    gameObject
    -0.35
    POSITIVE LOGITS
    XmlType
    0.67
    neſs
    0.60
    ieties
    0.60
    erees
    0.60
    ernalia
    0.59
    urezza
    0.59
    esses
    0.58
    élien
    0.58
    heses
    0.58
    naments
    0.57
    Activations Density 0.035%

    No Known Activations