© 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. 20-CLT-HP
    7. 75320
    Prev
    Next
    INDEX
    Explanations

    Bu

    np_max-act-logits · 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
     PublicKey
    -0.59
    mybatisplus
    -0.58
    AuthProvider
    -0.55
    rungsseite
    -0.54
    CJK
    -0.54
    setupUi
    -0.53
    บัติ
    -0.50
    例文帳に追加
    -0.49
    ItemBackground
    -0.49
    ToMany
    -0.49
    POSITIVE LOGITS
    คลิ
    0.47
    Rüyada
    0.46
     فريبيس
    0.46
    onan
    0.45
    nical
    0.44
     actionMode
    0.43
    न्ह
    0.43
    omeness
    0.42
    jstor
    0.42
     soin
    0.42
    Activations Density 0.002%

    No Known Activations