© 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. 5-CLT-HP
    7. 5884
    Prev
    Next
    INDEX
    Explanations

    or

    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
     Мексичка
    -0.85
     avoient
    -0.75
     financière
    -0.72
     nød
    -0.72
     vectorielle
    -0.72
     mourut
    -0.69
     étrangère
    -0.69
    ItemBackground
    -0.68
    MemoryWarning
    -0.67
     africaine
    -0.67
    POSITIVE LOGITS
     consider
    1.15
     take
    1.15
     find
    1.11
     try
    1.09
     ask
    1.06
     get
    1.06
     apply
    1.03
     go
    1.02
     choose
    1.02
     make
    1.00
    Activations Density 0.004%

    No Known Activations