© 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. 4-CLT-HP
    7. 2775
    Prev
    Next
    INDEX
    Explanations

    to

    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
    StringVar
    -0.50
     säll
    -0.47
     mať
    -0.47
     regulating
    -0.47
     Dete
    -0.47
     farlo
    -0.46
    ganggu
    -0.46
     communs
    -0.46
     kerül
    -0.45
     Thin
    -0.44
    POSITIVE LOGITS
    webElementXpaths
    0.82
    ViewFeatures
    0.82
    RenderAtEndOf
    0.73
    CreateModel
    0.70
    
    0.69
    WebElementEntity
    0.66
     OFDb
    0.65
    __':
    0.65
     say
    0.64
    IsContent
    0.61
    Activations Density 0.001%

    No Known Activations