© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74889
    Prev
    Next
    INDEX
    Explanations

    Technical/Non-English text

    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
    avez
    -0.42
     invokingState
    -0.41
     aload
    -0.40
    SLEEP
    -0.40
     itinéraires
    -0.40
    intele
    -0.37
     NSCoder
    -0.36
    BeforeAll
    -0.36
    ドラ
    -0.35
    lccn
    -0.33
    POSITIVE LOGITS
     LNB
    0.74
     الحره
    0.66
    martre
    0.65
    migrationBuilder
    0.64
    rawdę
    0.64
     myſelf
    0.64
    ItemBackground
    0.63
    ſelves
    0.63
     auffi
    0.62
    ghijklmnop
    0.62
    Activations Density 0.006%

    No Known Activations