© 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. 11554
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental studies and water management

    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
      
    -0.57
     street
    -0.56
     sub
    -0.50
     internet
    -0.48
     Street
    -0.47
     Internet
    -0.47
    street
    -0.47
     online
    -0.45
     rue
    -0.45
     room
    -0.44
    POSITIVE LOGITS
     dams
    1.08
     Dams
    0.90
     Efq
    0.90
     Irrigation
    0.86
     Watershed
    0.84
     watershed
    0.82
     resourceCulture
    0.81
     hydroelectric
    0.79
     irrig
    0.79
     дописавши
    0.77
    Activations Density 0.049%

    No Known Activations