© 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. 23358
    Prev
    Next
    INDEX
    Explanations

    references to the word "tar."

    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
    Vz
    -0.65
    Rudy
    -0.65
     Peoria
    -0.65
    Canton
    -0.63
     Oneida
    -0.62
    mogorov
    -0.60
     Microb
    -0.59
     Hoops
    -0.59
     UnityEngine
    -0.59
    :::
    -0.59
    POSITIVE LOGITS
     Tar
    1.57
    Tar
    1.52
     tar
    1.46
     TAR
    1.39
    tar
    1.34
    TAR
    1.27
     Taras
    1.03
    BeginContext
    0.98
    SequentialGroup
    0.90
     Taran
    0.89
    Activations Density 0.004%

    No Known Activations