© 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. 29552
    Prev
    Next
    INDEX
    Explanations

    references to commands or actions in a technical context

    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
    Portale
    -0.80
     Monfieur
    -0.79
     Chriftian
    -0.70
     Jefus
    -0.69
     Shakspeare
    -0.64
     haunts
    -0.62
    cropping
    -0.62
     poffe
    -0.60
     ویکی‌پدی
    -0.60
     Ilustra
    -0.60
    POSITIVE LOGITS
    MockMvc
    0.69
     put
    0.57
    ConstraintMaker
    0.57
    ņa
    0.55
    kmäler
    0.55
    磺
    0.52
     cast
    0.50
     already
    0.50
    ebenarnya
    0.48
    ")){
    0.47
    Activations Density 0.041%

    No Known Activations