© 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. 9304
    Prev
    Next
    INDEX
    Explanations

    the structure of sentences that include "is a" or similar phrases indicating definitions or descriptions

    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
     estekak
    -0.94
     otomatig
    -0.75
     AppBar
    -0.74
     незавершена
    -0.73
    saurus
    -0.70
    $_['
    -0.68
    ultuous
    -0.68
    EndGlobalSection
    -0.65
    glTexCoord
    -0.64
    sieur
    -0.63
    POSITIVE LOGITS
     distância
    0.48
     raggiung
    0.46
    AutoScale
    0.45
     (
    0.45
     A
    0.44
    ,
    0.41
     $
    0.40
     progetto
    0.40
    *
    0.40
     well
    0.39
    Activations Density 0.049%

    No Known Activations