© 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. 910
    Prev
    Next
    INDEX
    Explanations

    plasma

    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
     enfans
    -1.05
     متعلقه
    -1.03
     sauvages
    -1.02
     chré
    -1.01
     whoſe
    -1.00
     ainfi
    -1.00
     financières
    -1.00
     auroit
    -0.98
     complètes
    -0.97
     hâte
    -0.96
    POSITIVE LOGITS
    -
    0.62
    <bos>
    0.50
    '
    0.49
     movement
    0.47
     presence
    0.45
     activity
    0.45
     activities
    0.45
     sti
    0.45
     use
    0.42
     demands
    0.42
    Activations Density 0.009%

    No Known Activations