© 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. 21206
    Prev
    Next
    INDEX
    Explanations

    academic papers or preprints

    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
     تضيفلها
    -0.84
     Majefty
    -0.82
     pleaſure
    -0.80
     itſelf
    -0.71
     greateſt
    -0.69
     princesse
    -0.68
     ſever
    -0.68
     ſche
    -0.67
    ambilan
    -0.66
     ſy
    -0.65
    POSITIVE LOGITS
    awaiter
    0.52
    Hochspringen
    0.50
    gev
    0.45
    homonymie
    0.45
    atchi
    0.44
    onAttach
    0.44
     nau
    0.43
     private
    0.43
     plat
    0.41
     enca
    0.41
    Activations Density 0.039%

    No Known Activations