© 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. 1-CLT-HP
    7. 14190
    Prev
    Next
    INDEX
    Explanations

    formal deals or accords

    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
    IntoConstraints
    -0.85
     Agreements
    -0.81
    DockStyle
    -0.75
     prisonniers
    -0.73
     Agreement
    -0.70
     agreements
    -0.69
     gratuites
    -0.68
     ""],
    -0.68
    Agreement
    -0.66
     alimentaria
    -0.66
    POSITIVE LOGITS
    ANNES
    0.45
    intura
    0.40
     generally
    0.39
     Schindler
    0.39
     probably
    0.39
    writeFieldEnd
    0.38
     Baillargeon
    0.38
     concluded
    0.37
     Vall
    0.37
    cody
    0.36
    Activations Density 0.021%

    No Known Activations