© 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. 93874
    Prev
    Next
    INDEX
    Explanations

    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
    Бахар
    -0.56
    CodeAttribute
    -0.55
    ?',
    -0.52
     AUSSI
    -0.50
    atguigu
    -0.50
    ligg
    -0.49
    ()?
    -0.48
    )$/,
    -0.48
    BindView
    -0.47
    parsedMessage
    -0.45
    POSITIVE LOGITS
    يكب
    0.69
     समीक्षक
    0.60
     CreateTagHelper
    0.59
    Билгалдахарш
    0.59
     JpaRepository
    0.56
     himſelf
    0.55
     themſelves
    0.55
     spades
    0.54
     itſelf
    0.53
    Ane
    0.53
    Activations Density 0.002%

    No Known Activations