© 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. 3940
    Prev
    Next
    INDEX
    Explanations

    vitamins

    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
     ModelExpression
    -0.98
     againſt
    -0.88
    yntaxException
    -0.87
     pleaſure
    -0.84
     themſelves
    -0.79
     purpoſe
    -0.78
    NameInMap
    -0.78
     himſelf
    -0.77
     itſelf
    -0.74
     beginnetje
    -0.72
    POSITIVE LOGITS
     Mean
    0.49
     Live
    0.46
     mean
    0.46
     Water
    0.46
    ussis
    0.45
     végétale
    0.44
    -
    0.43
     Sea
    0.43
     Bel
    0.42
    id
    0.42
    Activations Density 0.003%

    No Known Activations