© 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. 128
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structural components related to programming code

    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
    OfWeek
    -0.68
    imte
    -0.62
    ATUR
    -0.59
     elect
    -0.55
     Wo
    -0.55
    อา
    -0.54
    OMI
    -0.52
    styleable
    -0.52
    badlogic
    -0.51
     aside
    -0.50
    POSITIVE LOGITS
    sizeCache
    0.83
    webElementXpaths
    0.65
     الرياضيه
    0.61
     صوتيه
    0.59
    posedge
    0.57
    ThroughAttribute
    0.55
     mxArray
    0.55
     spacy
    0.54
    ImageContext
    0.54
    InitVars
    0.54
    Activations Density 1.301%

    No Known Activations