© 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. 14410
    Prev
    Next
    INDEX
    Explanations

    references to studies and research results

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.58
     utafitiHapana
    -0.53
     vuitton
    -0.51
    upassen
    -0.51
    ParallelGroup
    -0.51
    utom
    -0.47
     referrerpolicy
    -0.47
     FICTION
    -0.47
     fiction
    -0.47
    SBATCH
    -0.46
    POSITIVE LOGITS
    الإنجليزية
    0.66
     définiti
    0.66
     scolaires
    0.66
     écrits
    0.62
     suivants
    0.61
    Hochspringen
    0.61
    featureID
    0.58
     pitié
    0.57
     habet
    0.56
    IntoConstraints
    0.56
    Activations Density 0.020%

    No Known Activations