© 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. 0-CLT-HP
    7. 42938
    Prev
    Next
    INDEX
    Explanations

    code and legal text

    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
    TestingModule
    -0.82
    AndEndTag
    -0.77
     MenuView
    -0.71
     سكانية
    -0.71
    EndContext
    -0.71
     TextAppearance
    -0.70
     propOrder
    -0.70
     NSCoder
    -0.68
     CGSize
    -0.67
    +#+#
    -0.67
    POSITIVE LOGITS
     .
    0.50
     />';
    0.45
    illi
    0.44
    bgp
    0.43
    XmlAccessType
    0.41
     '.
    0.40
    čaj
    0.40
    dom
    0.40
     OBITUARY
    0.40
    рович
    0.40
    Activations Density 1.574%

    No Known Activations