© 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. 76141
    Prev
    Next
    INDEX
    Explanations

    Specialized texts

    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
    GARET
    -0.53
     sub
    -0.50
    CloseOperation
    -0.50
     useSelector
    -0.50
    COLN
    -0.49
     traditionally
    -0.45
     conci
    -0.45
     vik
    -0.43
    ็จ
    -0.43
    isele
    -0.42
    POSITIVE LOGITS
     <=",
    0.65
     للاسماء
    0.63
    TintMode
    0.62
     Савезне
    0.62
    mobileqq
    0.60
     passés
    0.60
     <>",
    0.59
     hâte
    0.59
     avoient
    0.57
    oredCriteria
    0.57
    Activations Density 0.001%

    No Known Activations