Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 10564
    Prev
    Next
    INDEX
    Explanations

    code structure elements, such as brackets and function definitions

    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
     Efq
    -0.62
    xmlns
    -0.58
     juridiques
    -0.53
    BASEPATH
    -0.52
     indoss
    -0.52
     Jacobian
    -0.48
     chrétienne
    -0.47
    GraphicsUnit
    -0.46
     raiſ
    -0.46
    LookAnd
    -0.46
    POSITIVE LOGITS
    __':
    
    0.66
    saraba
    0.64
    "){
    
    0.63
     متعلقه
    0.58
    inguez
    0.57
    ]<<
    0.56
    ]){
    
    0.56
    ){
    
    0.55
    ()){
    
    0.55
    "):
    
    0.54
    Activations Density 0.064%

    No Known Activations