© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90668
    Prev
    Next
    INDEX
    Explanations

    worthiness

    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
     Textbook
    -0.60
     textbook
    -0.55
     Walkover
    -0.54
     financières
    -0.51
    momix
    -0.46
     alimentaires
    -0.45
     publiques
    -0.45
    ectoria
    -0.44
     textbooks
    -0.44
    latin
    -0.43
    POSITIVE LOGITS
    __(/*!
    0.87
     Efq
    0.79
    ]")]
    0.75
     springfox
    0.71
     gyhoeddwyd
    0.70
     Majefty
    0.70
     myſelf
    0.68
    modelBuilder
    0.68
     purpoſe
    0.66
     Monfieur
    0.66
    Activations Density 0.800%

    No Known Activations