© 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. 9152
    Prev
    Next
    INDEX
    Explanations

    numeric data and statistical results in a structured format, particularly related to measurements and percentages

    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
    disposing
    -0.54
    usty
    -0.46
     beg
    -0.45
     long
    -0.45
     man
    -0.43
    elo
    -0.43
    рк
    -0.42
     material
    -0.41
     ex
    -0.41
     human
    -0.40
    POSITIVE LOGITS
     '\\;'
    0.91
    IntoConstraints
    0.91
     pleaſure
    0.86
    Personendaten
    0.84
     EconPapers
    0.82
     للاسماء
    0.75
    +#+#
    0.75
     greateſt
    0.75
    IsContent
    0.73
     BoxDecoration
    0.73
    Activations Density 0.142%

    No Known Activations