© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 801
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and codes, likely related to source code or structured data formats

    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
     nahilalakip
    -0.88
    AccessorTable
    -0.78
    sizeCache
    -0.68
     المعيارى
    -0.67
     minOccurs
    -0.66
    stdio
    -0.66
     astore
    -0.59
    HasColumnType
    -0.58
    Xna
    -0.57
    Hentet
    -0.56
    POSITIVE LOGITS
     Majefty
    0.71
    省市镇
    0.59
     Monfieur
    0.59
     pleaſure
    0.57
    }();
    0.55
    canto
    0.54
     ſtate
    0.54
     Diver
    0.53
     Minang
    0.52
     principle
    0.52
    Activations Density 0.199%

    No Known Activations