© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5084
    Prev
    Next
    INDEX
    Explanations

    concepts related to the organization and management of data processing systems or algorithms

    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
     itſelf
    -1.02
     ―――――
    -0.98
    ]._
    -0.96
    StructEnd
    -0.93
    ſelf
    -0.89
     transfieras
    -0.88
    цездатний
    -0.87
    )");
    
    -0.85
     Theſe
    -0.85
    Geplaatst
    -0.85
    POSITIVE LOGITS
     waar
    0.42
     appunto
    0.41
    ↵
    0.40
     where
    0.40
    •
    0.40
     (
    0.40
     
    0.40
    "
    0.40
    -
    0.39
    where
    0.39
    Activations Density 1.256%

    No Known Activations