© 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. 11042
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols that may represent various coding or formatting elements

    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
    المناصب
    -0.88
     lenker
    -0.81
    AndEndTag
    -0.78
    WriteBarrier
    -0.76
    jsonwebtoken
    -0.75
    httphttps
    -0.74
     Efq
    -0.73
    Portale
    -0.73
     CreateTagHelper
    -0.72
    initComponents
    -0.71
    POSITIVE LOGITS
    aad
    0.58
    tä
    0.54
    孀
    0.50
    ẢN
    0.49
    — 
    0.49
     Deckel
    0.49
     Sore
    0.48
     picture
    0.48
    intendent
    0.48
    endphp
    0.48
    Activations Density 0.009%

    No Known Activations