© 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. 10122
    Prev
    Next
    INDEX
    Explanations

    probability

    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
     nakalista
    -0.68
     سكانية
    -0.66
     الحره
    -0.62
    ://$
    -0.62
     propOrder
    -0.61
     gereken
    -0.54
    UserScript
    -0.54
    ParallelGroup
    -0.54
     utafitiHapana
    -0.53
     يتيمه
    -0.52
    POSITIVE LOGITS
     pancreatitis
    0.55
    cyjna
    0.55
    pergillus
    0.52
     airway
    0.52
     renal
    0.52
    pectiva
    0.51
    llary
    0.51
    \}_{
    0.49
     pancreatic
    0.49
    udara
    0.49
    Activations Density 0.015%

    No Known Activations