© 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. 0-CLT-HP
    7. 41485
    Prev
    Next
    INDEX
    Explanations

    ending, decline, decrease

    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
     rise
    -1.05
    rise
    -0.81
     decline
    -0.75
    setVerticalGroup
    -0.71
     isolated
    -0.70
     يتيمه
    -0.70
    Rise
    -0.68
    decline
    -0.68
     Biôgrafia
    -0.66
    MLLoader
    -0.65
    POSITIVE LOGITS
    ات
    0.63
    s
    0.58
    ly
    0.52
    ies
    0.52
    黎
    0.52
    ities
    0.50
    ت
    0.50
    ️
    0.49
    es
    0.49
    os
    0.49
    Activations Density 0.125%

    No Known Activations