© 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. 1-CLT-HP
    7. 13348
    Prev
    Next
    INDEX
    Explanations

    along

    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
     along
    -0.67
     on
    -0.54
    wpi
    -0.48
     in
    -0.46
    はじめに
    -0.45
    expandindo
    -0.43
     for
    -0.43
    hatic
    -0.40
     ALONG
    -0.40
     supplied
    -0.40
    POSITIVE LOGITS
    ſelf
    0.96
     itſelf
    0.93
     pleaſure
    0.93
     myſelf
    0.89
     himſelf
    0.89
     themſelves
    0.88
     ſche
    0.88
     ſhould
    0.87
     uſe
    0.87
     ſtate
    0.87
    Activations Density 0.053%

    No Known Activations