© 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. 5-CLT-HP
    7. 293
    Prev
    Next
    INDEX
    Explanations

    shall

    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
     estekak
    -0.69
    WithIOException
    -0.67
    UnusedPrivate
    -0.63
    Rüyada
    -0.60
    InjectAttribute
    -0.59
    NegativeButton
    -0.55
     nahilalakip
    -0.55
    ImageContext
    -0.54
     Meksiku
    -0.53
    ).]
    -0.53
    POSITIVE LOGITS
    aryen
    0.55
    gameserver
    0.54
    bestimmung
    0.49
     smtplib
    0.49
    
    0.49
     getItemCount
    0.48
    GHz
    0.48
    Transkript
    0.48
    cells
    0.47
    ROL
    0.47
    Activations Density 0.001%

    No Known Activations