© 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. 92983
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    LookAnd
    -1.02
     <>",
    -0.83
     propOrder
    -0.82
    Autoritní
    -0.75
     فريبيس
    -0.73
     uska
    -0.72
     '\\;'
    -0.71
    Personendaten
    -0.71
    writeFieldEnd
    -0.71
     CreateTagHelper
    -0.70
    POSITIVE LOGITS
     GetComponent
    0.42
    (?)
    0.41
    this
    0.40
     (±
    0.40
    processData
    0.40
    ToDouble
    0.39
     earlier
    0.39
     Jednak
    0.39
    Бахар
    0.38
     Dlatego
    0.38
    Activations Density 0.025%

    No Known Activations