© 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. 93802
    Prev
    Next
    INDEX
    Explanations

    inquire

    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
     district
    -0.85
    MLLoader
    -0.81
    district
    -0.78
     Infórmanos
    -0.72
    σθαι
    -0.72
    department
    -0.71
     courants
    -0.71
     Delivered
    -0.70
     fallu
    -0.70
     igång
    -0.70
    POSITIVE LOGITS
    er
    0.66
     propOrder
    0.48
     CGPoint
    0.46
    mobileqq
    0.45
    ve
    0.44
    ER
    0.44
    CrossRef
    0.42
    nt
    0.42
    re
    0.42
    はじめに
    0.41
    Activations Density 0.066%

    No Known Activations