© 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. 94581
    Prev
    Next
    INDEX
    Explanations

    Ajax

    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
    mph
    -0.57
    ee
    -0.50
    hut
    -0.50
    gama
    -0.50
    der
    -0.49
    tal
    -0.48
    gins
    -0.47
     ee
    -0.47
    hash
    -0.47
    Ajax
    -0.45
    POSITIVE LOGITS
     CWE
    0.94
    IUrlHelper
    0.94
    Życiorys
    0.84
    rawDesc
    0.82
    InjectAttribute
    0.82
    jsdelivr
    0.81
    DotNetBar
    0.81
     BrowserModule
    0.78
     myſelf
    0.77
    HostException
    0.77
    Activations Density 1.010%

    No Known Activations