© 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. 287
    Prev
    Next
    INDEX
    Explanations

    structured data or code snippets with regions and associated parameters

    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
    ValueStyle
    -0.98
     isInitialized
    -0.80
     initComponents
    -0.74
    SharedDtor
    -0.71
     CURIAM
    -0.70
    webElement
    -0.69
    AsUp
    -0.68
    medriver
    -0.67
    ReusableCell
    -0.66
    Panamoan
    -0.65
    POSITIVE LOGITS
     ear
    0.55
     Ear
    0.55
     intermediate
    0.53
    intermediate
    0.52
    Intermediate
    0.52
    Ear
    0.51
    GLOBALS
    0.51
    fseek
    0.50
    idian
    0.49
    berly
    0.48
    Activations Density 3.599%

    No Known Activations