© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2233
    Prev
    Next
    INDEX
    Explanations

    repayment/reimbursement

    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
     sanitaires
    -0.66
     aapt
    -0.63
     CreateTagHelper
    -0.57
    DIPSETTING
    -0.56
     jambe
    -0.56
    AddHtmlAttribute
    -0.55
    ########.
    -0.53
    +#+
    -0.52
     médicaux
    -0.52
     énergé
    -0.51
    POSITIVE LOGITS
     creditors
    0.56
     للمعارف
    0.55
    QtCore
    0.55
    ]}"
    0.54
     lenders
    0.54
    kuuta
    0.54
     investors
    0.52
     loans
    0.50
    TagMode
    0.50
    )}+
    0.49
    Activations Density 0.002%

    No Known Activations