© 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. 10583
    Prev
    Next
    INDEX
    Explanations

    technical terms related to directory structures in file systems

    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
     transférez
    -1.11
     purpoſe
    -0.91
     reaſon
    -0.85
     Nunn
    -0.83
     pleaſure
    -0.82
     occaf
    -0.78
     Monfieur
    -0.77
     betweenstory
    -0.76
     ſmall
    -0.76
    ally
    -0.75
    POSITIVE LOGITS
     dir
    1.05
     Dir
    0.94
     dirs
    0.87
    Dir
    0.85
    dirs
    0.84
    PDIR
    0.78
    iverr
    0.76
    dir
    0.75
    DIR
    0.75
    ymce
    0.75
    Activations Density 0.016%

    No Known Activations