© 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. 19837
    Prev
    Next
    INDEX
    Explanations

    structural components and measurements in code and data descriptions

    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
     pubblic
    -0.49
     too
    -0.42
     isolato
    -0.42
    DoubleQuotes
    -0.42
    script
    -0.40
    intz
    -0.40
    ganu
    -0.39
     piede
    -0.38
     efect
    -0.37
     Crete
    -0.37
    POSITIVE LOGITS
    Tikang
    0.95
    ArrowToggle
    0.80
     Roskov
    0.79
    Hentet
    0.76
    IUrlHelper
    0.74
    SequentialGroup
    0.73
    saraba
    0.73
    يكب
    0.70
    ItemBackground
    0.70
    +:+
    0.69
    Activations Density 0.194%

    No Known Activations