© 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. 91928
    Prev
    Next
    INDEX
    Explanations

    securing private data

    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
    InjectAttribute
    -0.64
    OGND
    -0.52
    styleType
    -0.52
     thereon
    -0.49
    cshtml
    -0.48
    Портали
    -0.47
    paya
    -0.46
     Roskov
    -0.46
    ampang
    -0.46
     propOrder
    -0.46
    POSITIVE LOGITS
     >=",
    0.65
    RenderAtEndOf
    0.62
     UIKit
    0.56
    )))));
    0.55
     BoxFit
    0.54
    ⓧ
    0.52
     CommonModule
    0.52
     للمعارف
    0.49
    }")]
    0.48
     Element
    0.48
    Activations Density 0.080%

    No Known Activations