© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4302
    Prev
    Next
    INDEX
    Explanations

    tax

    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
    IUrlHelper
    -0.99
    IndentedString
    -0.92
    Tembelea
    -0.86
    principalColumn
    -0.84
    webElementXpaths
    -0.83
    RenderAtEndOf
    -0.83
    ValueStyle
    -0.82
    GEBURTSDATUM
    -0.81
     صوتيه
    -0.79
     Infórmanos
    -0.79
    POSITIVE LOGITS
    cha
    0.37
     như
    0.36
    long
    0.35
     moindre
    0.34
     wie
    0.33
     biais
    0.33
    bat
    0.33
    cra
    0.33
     como
    0.32
     long
    0.32
    Activations Density 0.002%

    No Known Activations