© 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. 39
    Prev
    Next
    INDEX
    Explanations

    references to technical or scientific components and processes

    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
     gouvernements
    -0.68
     attentes
    -0.68
    一位
    -0.64
     bénéfices
    -0.64
     réguli
    -0.63
     MaterialApp
    -0.63
     défis
    -0.62
     bienfaits
    -0.62
     pouvoirs
    -0.61
     définiti
    -0.61
    POSITIVE LOGITS
     jotka
    0.81
    ſelves
    0.80
    hips
    0.80
     themselves
    0.78
    Jaunes
    0.77
     are
    0.75
     които
    0.74
    citenamefont
    0.74
    יהם
    0.70
    يميديا
    0.68
    Activations Density 6.170%

    No Known Activations