© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14101
    Prev
    Next
    INDEX
    Explanations

    bank

    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
    -1.16
     disambiguazione
    -1.14
     banks
    -1.10
     Banks
    -1.05
     Bank
    -1.03
     BANK
    -0.98
    banks
    -0.97
    AddTagHelper
    -0.97
     BANKS
    -0.96
    Banks
    -0.94
    POSITIVE LOGITS
    reinterpret
    0.42
    solid
    0.39
    FZ
    0.39
     yetu
    0.39
    glEnd
    0.39
     diyor
    0.38
    rolling
    0.38
     ejus
    0.38
    able
    0.37
    lines
    0.36
    Activations Density 0.018%

    No Known Activations