© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6408
    Prev
    Next
    INDEX
    Explanations

    references to quantities and statistical data related to environmental sustainability

    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
    存于互联网档案馆
    -0.94
    NUMX
    -0.87
     insuffisamment
    -0.82
    etheless
    -0.79
     متعلقه
    -0.77
     كومونز
    -0.77
     Audiodateien
    -0.74
    rizona
    -0.73
     AspNetCore
    -0.73
     AssemblyProduct
    -0.72
    POSITIVE LOGITS
    !
    0.58
    antMatchers
    0.54
     Special
    0.52
    new
    0.51
     sizi
    0.51
     U
    0.50
     O
    0.50
     &
    0.50
     sconto
    0.49
    Special
    0.49
    Activations Density 0.183%

    No Known Activations