© 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. 4-CLT-HP
    7. 2094
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ValueStyle
    -0.58
     WebDriverWait
    -0.55
    ActionMode
    -0.47
    \{\\
    -0.47
    '][]
    -0.46
     partij
    -0.43
    kuuta
    -0.43
     iNdEx
    -0.41
    حوالہ
    -0.41
     sezione
    -0.40
    POSITIVE LOGITS
    :✨
    0.69
    politan
    0.68
    XmlAccessType
    0.67
    glers
    0.62
    WithMany
    0.61
    IVEREF
    0.58
    ourism
    0.58
    IBarButtonItem
    0.58
    ReferenceEquals
    0.57
    iseries
    0.55
    Activations Density 0.002%

    No Known Activations