© 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. 41428
    Prev
    Next
    INDEX
    Explanations

    skeletal

    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
     skeleton
    -0.86
     Framework
    -0.83
     bones
    -0.82
     framework
    -0.82
    ximity
    -0.81
     Skeletal
    -0.81
    framework
    -0.80
    AddTagHelper
    -0.80
    skeleton
    -0.80
    hésite
    -0.79
    POSITIVE LOGITS
     charge
    0.47
     failure
    0.46
     factor
    0.44
     enti
    0.44
     minister
    0.41
     tilla
    0.41
     suff
    0.40
     affer
    0.40
     man
    0.39
     esti
    0.39
    Activations Density 0.298%

    No Known Activations