© 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. 103
    Prev
    Next
    INDEX
    Explanations

    explain

    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
     igång
    -0.55
     to
    -0.55
    sizlik
    -0.49
     évé
    -0.47
     attirer
    -0.46
     choisis
    -0.44
     terlebih
    -0.44
    cherche
    -0.44
     đến
    -0.43
     battre
    -0.43
    POSITIVE LOGITS
    DeleteBehavior
    0.77
    OGND
    0.76
    awtextra
    0.67
    #
    0.66
    ScopeManager
    0.65
     للاسماء
    0.65
     فريبيس
    0.65
    sizeCache
    0.64
    الحياه
    0.61
     why
    0.58
    Activations Density 0.003%

    No Known Activations