© 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. 42624
    Prev
    Next
    INDEX
    Explanations

    muscle/bone

    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
     bone
    -0.64
    umbersome
    -0.62
     QtCore
    -0.54
     Grecs
    -0.54
    ViewImports
    -0.54
    Quiénes
    -0.54
     UITableView
    -0.53
     rossz
    -0.53
     ERSITY
    -0.53
     "":
    -0.52
    POSITIVE LOGITS
    zzleHttp
    0.60
    rups
    0.58
    setVerticalGroup
    0.57
    edos
    0.56
    setDo
    0.54
    edu
    0.53
    himu
    0.53
    strokes
    0.53
    ########.
    0.53
    ingway
    0.52
    Activations Density 0.067%

    No Known Activations