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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 288
    Prev
    Next
    INDEX
    Explanations

    code structure elements, particularly curly braces and parentheses

    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
     للمعارف
    -0.73
    )‏
    -0.68
     FetchType
    -0.65
    
    -0.65
    }_\
    -0.62
     Simba
    -0.62
     Tunisia
    -0.60
    ➋
    -0.60
     Juárez
    -0.59
     Tunisie
    -0.59
    POSITIVE LOGITS
     {
    1.55
     {
    1.27
    {{{
    1.27
    ({
    1.23
    __':
    1.22
    {
    1.17
    {
    1.16
    |{
    1.14
    ++){
    1.13
    >{
    1.13
    Activations Density 0.688%

    No Known Activations