© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4947
    Prev
    Next
    INDEX
    Explanations

    code and numbers

    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
    buttonBar
    -0.66
    Diweddarwch
    -0.63
    ArrowToggle
    -0.60
    MigrationBuilder
    -0.59
     five
    -0.58
     four
    -0.58
    Four
    -0.57
     Four
    -0.56
    nloa
    -0.56
    Portale
    -0.55
    POSITIVE LOGITS
    sendRedirect
    0.52
     considérons
    0.47
     useParams
    0.46
    trude
    0.45
    webElement
    0.43
    LocalizedString
    0.42
    ależy
    0.41
    warf
    0.41
    enumii
    0.40
    9
    0.40
    Activations Density 0.020%

    No Known Activations