© 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. 1-CLT-HP
    7. 15407
    Prev
    Next
    INDEX
    Explanations

    need

    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
    contentLoaded
    -0.59
    ؤلاء
    -0.59
    EnableWeb
    -0.58
     propOrder
    -0.57
    rifty
    -0.54
    WriteTagHelper
    -0.52
    haway
    -0.51
     '\\;'
    -0.50
    Према
    -0.49
     capitalists
    -0.48
    POSITIVE LOGITS
     cardiac
    0.54
     Cardiac
    0.53
     للاسماء
    0.52
    IonicModule
    0.52
     serial
    0.52
    iben
    0.51
     mostrarán
    0.50
    Portale
    0.50
    Cardiac
    0.50
     esophageal
    0.49
    Activations Density 0.068%

    No Known Activations