© 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. 14479
    Prev
    Next
    INDEX
    Explanations

    numerical sequences or identifiers

    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
    ParallelGroup
    -0.77
    styleType
    -0.66
    DockStyle
    -0.66
    ChildScrollView
    -0.65
     ProtoMessage
    -0.65
    mybatisplus
    -0.63
    tonode
    -0.60
     SEDS
    -0.60
    DatabaseError
    -0.59
    richTextPanel
    -0.59
    POSITIVE LOGITS
     Majefty
    0.68
     pleaſure
    0.66
     uſe
    0.63
    šanu
    0.61
     uſed
    0.61
     themſelves
    0.60
     poffible
    0.60
     ſen
    0.59
    šanai
    0.59
     ſmall
    0.58
    Activations Density 0.001%

    No Known Activations