© 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. 22450
    Prev
    Next
    INDEX
    Explanations

    references to other items or entities, indicating a pattern of inclusion or contrast

    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
    Not in Any Lists

    No Comments

    Negative Logits
     another
    -0.62
    ItemLayout
    -0.60
    another
    -0.59
    AsUp
    -0.59
    PerformLayout
    -0.58
    yntaxException
    -0.57
     umane
    -0.57
     Partager
    -0.57
    bewerken
    -0.52
    ActionMode
    -0.51
    POSITIVE LOGITS
    XmlAccessType
    1.09
     समीक्षाओं
    0.68
     Estudios
    0.63
     Архів
    0.62
    mitian
    0.59
    }}">
    0.58
    lotl
    0.58
     autorytatywna
    0.56
     disambiguazione
    0.56
    MMdd
    0.56
    Activations Density 0.012%

    No Known Activations