© 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. 43060
    Prev
    Next
    INDEX
    Explanations

    medi

    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
    med
    -1.55
     med
    -1.44
     medi
    -1.37
    medi
    -1.36
    Med
    -1.28
     Med
    -1.26
    MED
    -1.23
     mediate
    -1.14
     MED
    -1.10
    Medi
    -1.08
    POSITIVE LOGITS
    stateProvider
    0.85
     يتيمه
    0.84
    Personensuche
    0.84
     itſelf
    0.83
    TestingModule
    0.76
     متعلقه
    0.72
    MemoryWarning
    0.71
    EndInit
    0.71
     iſt
    0.70
    ViewImports
    0.69
    Activations Density 0.116%

    No Known Activations