© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 2321
    Prev
    Next
    INDEX
    Explanations

    references to kernels and kernel-related concepts in statistical or computational contexts

    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
    mybatisplus
    -0.94
    httphttps
    -0.91
    :✨
    -0.87
     *++
    -0.85
     Nawaz
    -0.84
    SuppressMessage
    -0.83
    σιμοποι
    -0.82
     InputDecoration
    -0.82
     Shakspeare
    -0.80
    Personensuche
    -0.79
    POSITIVE LOGITS
     kernel
    1.50
     kernels
    1.41
    kernel
    1.38
     Kernel
    1.34
    Kernel
    1.26
     Ker
    1.18
     KERN
    1.06
    KERNEL
    1.03
    Ker
    0.96
    kernels
    0.96
    Activations Density 0.027%

    No Known Activations