© 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. 0-CLT-HP
    7. 41819
    Prev
    Next
    INDEX
    Explanations

    1

    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
    RegistryLite
    -0.74
     suivants
    -0.59
    bootstrapcdn
    -0.56
     financières
    -0.56
     avancée
    -0.56
     bucal
    -0.56
     fırs
    -0.56
     énergé
    -0.55
     pysty
    -0.54
     Puis
    -0.53
    POSITIVE LOGITS
    
    0.63
    </tfoot>
    0.59
    Xna
    0.58
    地看着
    0.56
    RetentionPolicy
    0.55
    StoryboardSegue
    0.55
    :+:
    0.53
    setViewportView
    0.53
     defaultstate
    0.53
    Rüyada
    0.53
    Activations Density 0.275%

    No Known Activations