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. 8876
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and equations

    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
     Мексичка
    -0.89
     mergeFrom
    -0.73
     vectorielles
    -0.61
     juridiques
    -0.60
    WithIOException
    -0.59
    reactstrap
    -0.56
     OMITBAD
    -0.56
    ContentAsync
    -0.53
    toContain
    -0.53
    újo
    -0.52
    POSITIVE LOGITS
    IsContent
    0.63
     الرياضيه
    0.57
     Dafür
    0.55
     ganglia
    0.53
     Там
    0.52
     <",
    0.50
     lenker
    0.49
     widths
    0.48
     ones
    0.47
     Correspond
    0.47
    Activations Density 0.425%

    No Known Activations