© 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. 23242
    Prev
    Next
    INDEX
    Explanations

    HTML/XML tags and their attributes

    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
    aquarium
    -0.83
    tamment
    -0.82
    Personendaten
    -0.75
     Waray
    -0.74
     Vedas
    -0.73
    EventBus
    -0.72
    ICLES
    -0.72
    μφωνα
    -0.72
    wnętr
    -0.71
    endroit
    -0.71
    POSITIVE LOGITS
     Auss
    0.74
    pezi
    0.72
     quitt
    0.71
    ground
    0.69
    ReusableCell
    0.68
     McKe
    0.68
    utor
    0.66
    ers
    0.65
     McCall
    0.64
    holde
    0.64
    Activations Density 0.021%

    No Known Activations