© 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. 5580
    Prev
    Next
    INDEX
    Explanations

    financial transactions

    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
     têtes
    -0.50
     chré
    -0.49
     hôtes
    -0.47
     meilleures
    -0.47
     vectoriales
    -0.46
     enfans
    -0.46
     peuples
    -0.46
    +#+
    -0.46
     boî
    -0.45
     pouvoirs
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.69
     jScrollPane
    0.65
    pires
    0.64
    sizeCache
    0.63
     tartalomajánló
    0.63
    SequentialGroup
    0.61
    UserScript
    0.60
    urons
    0.60
     zeros
    0.58
     الحره
    0.58
    Activations Density 0.000%

    No Known Activations