© 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. 1-CLT-HP
    7. 9845
    Prev
    Next
    INDEX
    Explanations

    pick

    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
     respeito
    -0.49
     organisée
    -0.49
     který
    -0.48
     carelessness
    -0.48
     ktorý
    -0.48
     scelte
    -0.47
     possesso
    -0.46
     kohdetta
    -0.45
    utilisons
    -0.45
     respeto
    -0.44
    POSITIVE LOGITS
     Autorisations
    0.70
     Réponses
    0.61
    PreferredItem
    0.59
    GraphicsUnit
    0.59
     Ven
    0.59
    master
    0.59
     nahilalakip
    0.57
    IVEREF
    0.56
     חיצוניים
    0.55
     MainAxisSize
    0.55
    Activations Density 0.011%

    No Known Activations