© 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. 25362
    Prev
    Next
    INDEX
    Explanations

    TODO comments or tasks in code

    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
    tvguidetime
    -0.56
     getM
    -0.51
     Pack
    -0.48
     pack
    -0.46
    irão
    -0.45
    monial
    -0.43
    GOTREF
    -0.43
     ngang
    -0.43
    échal
    -0.42
    UserEntity
    -0.42
    POSITIVE LOGITS
     TODO
    0.99
    TODO
    0.96
    DockStyle
    0.93
    todo
    0.84
    Todo
    0.83
    ToDo
    0.79
     Todo
    0.73
    memoized
    0.73
    WithIOException
    0.73
    DOCTYPE
    0.72
    Activations Density 0.002%

    No Known Activations