© 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. 29064
    Prev
    Next
    INDEX
    Explanations

    elements related to metadata or object attributes in a structured format

    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
    RegressionTest
    -0.60
    andaag
    -0.57
    CloseOperation
    -0.57
    IBarButtonItem
    -0.54
    enegal
    -0.53
     ParseException
    -0.53
     الحره
    -0.52
     denk
    -0.51
     Superhost
    -0.51
    denominator
    -0.49
    POSITIVE LOGITS
     ſta
    0.66
    otras
    0.65
     ſeveral
    0.62
     devriez
    0.61
     "..\..\
    0.59
     ſtand
    0.57
    keyColumn
    0.55
     ſol
    0.55
    MBC
    0.55
    thums
    0.55
    Activations Density 0.002%

    No Known Activations