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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91935
    Prev
    Next
    INDEX
    Explanations

    finance

    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
     bank
    -1.01
    SequentialGroup
    -0.93
     banking
    -0.91
     banks
    -0.90
    bank
    -0.84
     BANKS
    -0.82
     BANK
    -0.82
     bancaire
    -0.80
    BANK
    -0.79
    DialogContent
    -0.79
    POSITIVE LOGITS
    s
    0.53
     Thess
    0.46
     Atlantic
    0.45
     affinity
    0.42
    ios
    0.41
     index
    0.41
    WriteAttribute
    0.40
    note
    0.40
     tube
    0.40
    ↵↵
    0.39
    Activations Density 0.138%

    No Known Activations