© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 18890
    Prev
    Next
    INDEX
    Explanations

    references to a specific compound or treatment known as TZ

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Roskov
    -0.94
    RegressionTest
    -0.88
    XtraEditors
    -0.86
     Aene
    -0.85
    dafx
    -0.84
    QMetaType
    -0.82
     itſelf
    -0.82
     myſelf
    -0.80
    PreExecute
    -0.77
     fabia
    -0.76
    POSITIVE LOGITS
     tz
    1.42
    tz
    1.36
     TZ
    1.32
    TZ
    1.29
     Tz
    1.23
    Tz
    1.19
    ntz
    0.66
    omenclature
    0.64
     Ts
    0.63
     Nes
    0.63
    Activations Density 0.001%

    No Known Activations