© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11677
    Prev
    Next
    INDEX
    Explanations

    risk

    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
    ky
    -0.52
    ab
    -0.52
    inject
    -0.51
    AsUp
    -0.47
    tled
    -0.47
     Wren
    -0.46
    open
    -0.45
    Przypisy
    -0.44
     Em
    -0.44
     ferner
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.64
     Оно
    0.61
     الرياضيه
    0.60
    getStatusCode
    0.60
    WebVitals
    0.59
    AutoScaleMode
    0.59
    IGraphics
    0.58
    IBOutlet
    0.57
    CodeAttribute
    0.56
     ComVisible
    0.55
    Activations Density 0.005%

    No Known Activations