© 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. 4-CLT-HP
    7. 1408
    Prev
    Next
    INDEX
    Explanations

    although/though

    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
    DockStyle
    -0.50
     surla
    -0.48
    الحياه
    -0.47
    Viitteet
    -0.43
    FontStyle
    -0.43
     autorytatywna
    -0.43
     pinulongan
    -0.42
     implementation
    -0.42
     Heads
    -0.41
    erialize
    -0.41
    POSITIVE LOGITS
     HasFactory
    0.59
     now
    0.59
     not
    0.59
     spelled
    0.55
     often
    0.55
     usually
    0.53
    CloseOperation
    0.53
     best
    0.52
    ittarius
    0.52
     generally
    0.50
    Activations Density 0.035%

    No Known Activations