© 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. 26944
    Prev
    Next
    INDEX
    Explanations

    phrases indicating limitations in research studies

    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
    bitField
    -0.55
    kreuz
    -0.50
    inan
    -0.48
    __
    -0.46
    WithIOException
    -0.46
    aarrggbb
    -0.45
    pushFollow
    -0.44
     suele
    -0.44
    łk
    -0.43
     soos
    -0.43
    POSITIVE LOGITS
     contextLoads
    0.66
     AppColors
    0.66
    PerformLayout
    0.65
    RuleContext
    0.60
    interopRequire
    0.60
    íncia
    0.58
    auce
    0.57
    inerja
    0.57
    OrWhiteSpace
    0.57
     geblieben
    0.56
    Activations Density 0.043%

    No Known Activations