© 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. 93628
    Prev
    Next
    INDEX
    Explanations

    technical/scientific context

    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
    TextSpan
    -0.57
    })*/
    -0.56
    Vis
    -0.56
    dafx
    -0.53
     Arcane
    -0.52
     SAX
    -0.51
     Esau
    -0.51
     smoke
    -0.50
     Sancho
    -0.49
     shepherds
    -0.49
    POSITIVE LOGITS
    Encyclopædia
    0.55
     Мексичка
    0.55
    adə
    0.52
    \}\\
    0.51
    
    0.49
    RegressionTest
    0.48
    ercises
    0.48
     <<<<<<<<<<<<<<
    0.47
     quelcon
    0.47
    UnitTesting
    0.47
    Activations Density 0.011%

    No Known Activations