© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98276
    Prev
    Next
    INDEX
    Explanations

    legal and news documents

    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
    IComponent
    -0.65
     שוליים
    -0.65
    windowFixed
    -0.65
    MessageTagHelper
    -0.64
    ValueStyle
    -0.64
    MeasureSpec
    -0.63
     Normdatei
    -0.60
     समीक्षाओं
    -0.59
    WebElementEntity
    -0.59
    RenderAtEndOf
    -0.57
    POSITIVE LOGITS
    __":
    0.60
    HostException
    0.51
    Hozzáférés
    0.50
     honeymoon
    0.49
     Dooley
    0.48
     zda
    0.48
     BorderSide
    0.47
     LoggerFactory
    0.46
    utzung
    0.45
     exhale
    0.45
    Activations Density 0.005%

    No Known Activations