© 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. 6053
    Prev
    Next
    INDEX
    Explanations

    specific technical notations or variables in mathematical or scientific expressions

    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
    randomUUID
    -0.66
     sv
    -0.58
    NewGuid
    -0.55
    penup
    -0.55
    orteur
    -0.53
    Sv
    -0.52
     idéia
    -0.52
    JdbcTemplate
    -0.52
     svo
    -0.51
    newArrayList
    -0.50
    POSITIVE LOGITS
    Personensuche
    0.81
    DispatchToProps
    0.68
    <bos>
    0.64
     transférez
    0.63
    Hochspringen
    0.63
     HasFactory
    0.62
    pensive
    0.59
    χρι
    0.56
    mallow
    0.56
    الدراسه
    0.56
    Activations Density 0.220%

    No Known Activations