© 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. 20-CLT-HP
    7. 76841
    Prev
    Next
    INDEX
    Explanations

    French words

    np_max-act-logits · 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
    DockStyle
    -0.81
     hx
    -0.81
    IonicModule
    -0.80
     ETI
    -0.80
     CURIAM
    -0.80
    
    -0.76
    ValueStyle
    -0.75
    Бахар
    -0.73
     didactic
    -0.72
     anatomic
    -0.72
    POSITIVE LOGITS
     caméra
    0.42
     ruban
    0.42
     spectateurs
    0.41
     vété
    0.41
     héri
    0.41
     ordinaire
    0.40
     intérieure
    0.39
     ordinaires
    0.38
     aveug
    0.38
    nanoTime
    0.37
    Activations Density 0.000%

    No Known Activations