© 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. 20352
    Prev
    Next
    INDEX
    Explanations

    numerical data and technical parameters related to networking and system configurations

    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
    HTH
    -0.54
     Luce
    -0.47
    platt
    -0.44
     cable
    -0.44
    苷
    -0.44
    بر
    -0.44
    ----</
    -0.44
     GF
    -0.42
    ])));
    -0.42
    ctez
    -0.42
    POSITIVE LOGITS
    ReusableCell
    0.81
     beginnetje
    0.79
     initComponents
    0.79
     /\.(
    0.69
     Dernière
    0.69
     المعيارى
    0.66
    
    0.60
    arraycopy
    0.59
    AISSEE
    0.59
     JpaRepository
    0.59
    Activations Density 0.094%

    No Known Activations