© 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. 1579
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
    
    -0.84
    AndEndTag
    -0.81
     AssemblyCulture
    -0.80
    Captor
    -0.80
     незавершена
    -0.79
    LookAnd
    -0.77
     Efq
    -0.75
    setVerticalGroup
    -0.74
    fromnode
    -0.73
    ValueGenerated
    -0.73
    POSITIVE LOGITS
     tanke
    0.43
     to
    0.40
     of
    0.40
     some
    0.39
     deep
    0.39
    ate
    0.39
    theless
    0.39
     a
    0.39
     already
    0.38
    tize
    0.38
    Activations Density 0.075%

    No Known Activations