© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16100
    Prev
    Next
    INDEX
    Explanations

    interface

    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
    Negative Logits
     interface
    -1.25
    interface
    -1.20
     Interface
    -1.16
    Interface
    -1.14
     interfaces
    -1.05
     INTERFACE
    -0.93
     Interfaces
    -0.91
     интерфей
    -0.85
     interfaz
    -0.83
    interfaces
    -0.81
    POSITIVE LOGITS
    providedIn
    0.97
    ьаж
    0.84
    writeFieldEnd
    0.83
    QMetaType
    0.77
    tonsoft
    0.77
    UnusedPrivate
    0.76
    SpringBootTest
    0.76
    SpringRunner
    0.75
    tonode
    0.74
     doInBackground
    0.74
    Activations Density 0.035%

    No Known Activations