© 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. 51
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and calculations involving remainders

    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
    WEBPACK
    -0.61
    ConstraintMaker
    -0.61
    addPreferredGap
    -0.58
     established
    -0.56
     مشين
    -0.56
    extAlignment
    -0.55
    tagHelperRunner
    -0.55
     inoxidable
    -0.53
    FEAT
    -0.53
     envisioned
    -0.53
    POSITIVE LOGITS
    djangoproject
    0.79
    зулта
    0.74
    Personensuche
    0.71
     typelib
    0.69
    Solución
    0.66
    SharedCtor
    0.62
     nahilalakip
    0.61
    DropColumn
    0.61
    writerow
    0.59
     kasarigan
    0.56
    Activations Density 2.121%

    No Known Activations