© 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. 5-CLT-HP
    7. 94371
    Prev
    Next
    INDEX
    Explanations

    narratives

    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
    __(/*!
    -0.86
     AssemblyCulture
    -0.83
    StoryboardSegue
    -0.65
    ]--;
    -0.64
     CreateTagHelper
    -0.59
    TemporalType
    -0.57
    nodoc
    -0.57
     "..\..\..\
    -0.56
    IBOutlet
    -0.56
     Când
    -0.56
    POSITIVE LOGITS
     vérit
    0.53
    basicConfig
    0.51
     he
    0.50
     waaronder
    0.49
    styleType
    0.49
     incluindo
    0.49
     verdaderas
    0.48
    uebe
    0.48
     most
    0.48
     ninguno
    0.48
    Activations Density 0.003%

    No Known Activations