© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 757
    Prev
    Next
    INDEX
    Explanations

    single letters

    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
     E
    -0.49
    WithIOException
    -0.48
    ']))
    -0.46
    "]));
    -0.43
     numberOfRows
    -0.43
    IUrlHelper
    -0.43
    ьаж
    -0.43
    }))
    -0.43
     WaitForSeconds
    -0.43
    HttpPut
    -0.42
    POSITIVE LOGITS
    مصادر
    0.73
     leſs
    0.66
     courseId
    0.66
     myſelf
    0.62
     itſelf
    0.62
     pleaſure
    0.60
     AppColors
    0.59
     joaat
    0.58
     Wikidata
    0.56
    مراجع
    0.56
    Activations Density 0.004%

    No Known Activations