© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2519
    Prev
    Next
    INDEX
    Explanations

    with

    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
    السكان
    -0.85
     pinulongan
    -0.85
    Бахар
    -0.82
    ItemBackground
    -0.79
    InitVars
    -0.74
     internetowa
    -0.74
    opress
    -0.74
    Their
    -0.74
     Autorisations
    -0.71
    yelitis
    -0.71
    POSITIVE LOGITS
     the
    0.66
     or
    0.61
     a
    0.57
     this
    0.55
    ,
    0.53
     all
    0.50
     it
    0.46
     each
    0.45
     room
    0.44
     of
    0.44
    Activations Density 0.001%

    No Known Activations