© 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. 0-CLT-HP
    7. 93538
    Prev
    Next
    INDEX
    Explanations

    ankle

    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
     ankle
    -0.72
     inequality
    -0.66
     Ankle
    -0.61
     Inequality
    -0.59
    Ine
    -0.57
    inigungs
    -0.51
    SuccessListener
    -0.48
     unwilling
    -0.47
    ens
    -0.45
     FormBuilder
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.77
    theless
    0.71
     بيها
    0.67
    ſelf
    0.63
     againſt
    0.62
     leſs
    0.62
     Jefus
    0.61
    withstanding
    0.61
     ſhall
    0.60
    ślę
    0.59
    Activations Density 0.050%

    No Known Activations