© 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. 1-CLT-HP
    7. 9996
    Prev
    Next
    INDEX
    Explanations

    Government and organizations

    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
     kaarangay
    -0.95
    RenderAtEndOf
    -0.91
    DeleteBehavior
    -0.86
    writeFieldEnd
    -0.84
    انيف
    -0.83
     kasarigan
    -0.83
     يتيمه
    -0.82
     Roskov
    -0.80
     Baillargeon
    -0.78
    adpleegd
    -0.77
    POSITIVE LOGITS
     wind
    0.52
     R
    0.51
     Lord
    0.41
    /
    0.40
    R
    0.39
     onPage
    0.38
     Wind
    0.38
     space
    0.37
     /
    0.37
     Space
    0.37
    Activations Density 0.005%

    No Known Activations