Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14074
    Prev
    Next
    INDEX
    Explanations

    words related to drug addiction and treatment with methadone

    oai_token-act-pair · gemini-2.0-flash

    withdrawal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ISNI
    -0.61
     Roskov
    -0.60
    SourceChecksum
    -0.59
     AppCompatTheme
    -0.56
     الدولى
    -0.54
     Semantics
    -0.53
     Dyson
    -0.52
    QApplication
    -0.52
     surla
    -0.52
    yscy
    -0.51
    POSITIVE LOGITS
     withdrawal
    1.05
     Withdrawal
    0.90
    withdrawal
    0.83
     withdrawals
    0.83
    Withdrawal
    0.76
     withdraw
    0.73
     Withdraw
    0.73
     withdraws
    0.68
     withdrawing
    0.67
    withdraw
    0.66
    Activations Density 2.365%

    No Known Activations