© 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. 2535
    Prev
    Next
    INDEX
    Explanations

    Louis/Lewis

    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
     GenerationType
    -0.80
    DockStyle
    -0.73
     '\\;'
    -0.66
     IndexPath
    -0.65
     صوتيه
    -0.65
     ostavi
    -0.64
    styleType
    -0.63
     ProtoMessage
    -0.62
    JpaRepository
    -0.60
     handleMessage
    -0.60
    POSITIVE LOGITS
     Stevenson
    0.54
    getAs
    0.47
    mende
    0.47
    me
    0.46
     B
    0.46
     Balfour
    0.46
     vuitton
    0.45
     mon
    0.44
    ine
    0.43
    postDelayed
    0.43
    Activations Density 0.006%

    No Known Activations