© 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. 3668
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Autoritní
    -0.90
    ScopeManager
    -0.82
    Personendaten
    -0.80
    Hozzáférés
    -0.79
     venons
    -0.77
     consultato
    -0.76
    IsMutable
    -0.74
    TestingModule
    -0.74
    IsContent
    -0.72
    AccessorTable
    -0.72
    POSITIVE LOGITS
    #
    0.40
    IB
    0.39
     dalam
    0.38
    vábbi
    0.38
     aquel
    0.37
    `
    0.35
     valueForKey
    0.35
    ,"
    0.34
    HtmlAttribute
    0.34
    ほうがいい
    0.34
    Activations Density 0.010%

    No Known Activations