© 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. 19865
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds or reagents used in laboratory settings

    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
    <h3>
    -0.61
     \%$\\
    -0.61
    🔥🔥
    -0.61
    EReference
    -0.61
    rmızı
    -0.60
     lilies
    -0.60
     mê
    -0.59
     Excavation
    -0.59
     ACI
    -0.58
     Carr
    -0.57
    POSITIVE LOGITS
     Tween
    1.69
    Tween
    1.22
     tween
    1.12
    tween
    1.03
    WEEN
    0.82
    ween
    0.81
     виправивши
    0.81
     twe
    0.80
     Twe
    0.73
    AdapterView
    0.73
    Activations Density 0.001%

    No Known Activations