© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11838
    Prev
    Next
    INDEX
    Explanations

    frequency

    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
    SharedCtor
    -0.64
     translateY
    -0.57
    ücks
    -0.57
     ODS
    -0.54
     Bertram
    -0.54
    cator
    -0.52
    chii
    -0.51
     Sando
    -0.51
     Stol
    -0.50
     globular
    -0.50
    POSITIVE LOGITS
    SuccessListener
    0.62
    expandindo
    0.61
    HasForeignKey
    0.59
    Népesség
    0.58
     IBOutlet
    0.57
     disambiguazione
    0.56
    DataMember
    0.56
    PerformLayout
    0.55
     kotlinx
    0.55
    WebControls
    0.54
    Activations Density 0.009%

    No Known Activations