© 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. 3402
    Prev
    Next
    INDEX
    Explanations

    brains

    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
     ExecuteAsync
    -0.75
     متعلقه
    -0.71
    abatic
    -0.65
     disambiguazione
    -0.63
     betweenstory
    -0.62
    addCriterion
    -0.62
    :✨
    -0.60
    __(/*!
    -0.60
    balleur
    -0.60
     FontWeight
    -0.59
    POSITIVE LOGITS
     to
    0.61
    .
    0.52
     Function
    0.50
     function
    0.49
    Reagents
    0.45
     in
    0.45
    Function
    0.43
     Functions
    0.42
     achtergrond
    0.42
     pasada
    0.42
    Activations Density 0.000%

    No Known Activations