© 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. 31930
    Prev
    Next
    INDEX
    Explanations

    references to post hoc analysis

    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
     
    -0.59
    primaryColor
    -0.52
     the
    -0.48
    Dougall
    -0.48
     åt
    -0.48
     лице
    -0.48
    Spoljašnje
    -0.46
     land
    -0.46
    deny
    -0.46
     Ples
    -0.46
    POSITIVE LOGITS
     hoc
    1.25
     تانيه
    1.16
     Hoc
    1.11
    hoc
    1.09
     propOrder
    1.00
    Hoc
    0.99
    Personensuche
    0.99
    RegressionTest
    0.94
    Geplaatst
    0.90
    abestanden
    0.90
    Activations Density 0.001%

    No Known Activations