© 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. 11271
    Prev
    Next
    INDEX
    Explanations

    comparative terms indicating a higher degree or quantity

    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
    insee
    -0.61
    iseite
    -0.58
     great
    -0.57
     stuff
    -0.57
    arote
    -0.57
     Cut
    -0.57
    Cut
    -0.57
    scen
    -0.57
    zünd
    -0.56
    ]=="
    -0.56
    POSITIVE LOGITS
    Sucesor
    0.88
    Greater
    0.83
     Chia
    0.83
    astify
    0.83
     Soma
    0.81
    titleMargin
    0.81
     Kelley
    0.78
    AddTagHelper
    0.78
     photolibrary
    0.78
    GREATER
    0.78
    Activations Density 0.016%

    No Known Activations