© 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. 29125
    Prev
    Next
    INDEX
    Explanations

    documentation or summaries related to code structures or classes

    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
     itſelf
    -0.83
     uſed
    -0.82
     chofe
    -0.81
     houſe
    -0.79
     poffe
    -0.76
     raiſ
    -0.74
     pylint
    -0.74
     surla
    -0.74
    apunov
    -0.73
    íncia
    -0.73
    POSITIVE LOGITS
     CreateTagHelper
    0.72
    bro
    0.56
    flex
    0.54
     "
    0.51
    gem
    0.51
     '
    0.51
    lav
    0.49
     cref
    0.48
    summary
    0.47
     To
    0.46
    Activations Density 0.000%

    No Known Activations