© 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. 0-CLT-HP
    7. 93122
    Prev
    Next
    INDEX
    Explanations

    )

    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
    ,
    -0.56
     so
    -0.47
    Odkazy
    -0.45
     if
    -0.44
     able
    -0.43
    XmlEnum
    -0.43
     me
    -0.40
     fact
    -0.39
     false
    -0.38
     je
    -0.38
    POSITIVE LOGITS
    AddTagHelper
    0.85
    RenderAtEndOf
    0.83
    RectangleBorder
    0.81
    SourceChecksum
    0.79
     ainfi
    0.75
    ChildScrollView
    0.75
    uxxxx
    0.74
     itſelf
    0.72
     themſelves
    0.72
     avesse
    0.72
    Activations Density 0.325%

    No Known Activations