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. 14339
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to gauge theories

    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
    yargs
    -0.57
     Staffel
    -0.53
     aset
    -0.51
     rayos
    -0.49
    日起
    -0.46
    ficheiro
    -0.46
     ('
    -0.46
     universel
    -0.46
     degré
    -0.45
     sopra
    -0.45
    POSITIVE LOGITS
    PyExc
    0.77
     >",
    0.76
    grà
    0.72
    Geplaatst
    0.69
     pinulongan
    0.69
    ".
    
    0.69
    OwnProperty
    0.69
     $_"
    0.69
     otomatig
    0.69
     useAppContext
    0.67
    Activations Density 0.027%

    No Known Activations