© 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. 14519
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of components in a machinery or engineering context

    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
     iub
    -0.51
     fuis
    -0.48
     quitte
    -0.44
     perfetto
    -0.43
     alegria
    -0.42
     chiar
    -0.41
     exitoso
    -0.41
     misses
    -0.41
     felice
    -0.41
     adem
    -0.40
    POSITIVE LOGITS
    +#+#
    0.96
    OGND
    0.92
    ]--;
    0.88
     kasarigan
    0.85
    Datuak
    0.84
    GEBURTSDATUM
    0.84
    PhysRev
    0.82
     NgModule
    0.81
     TextAppearance
    0.81
    LabelTagHelper
    0.81
    Activations Density 0.159%

    No Known Activations