© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 18149
    Prev
    Next
    INDEX
    Explanations

    terms related to endangered species and conservation

    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
    Negative Logits
    figer
    -0.65
    Enllaces
    -0.56
     tả
    -0.54
    Kosten
    -0.51
     partielle
    -0.50
     estekak
    -0.50
     Baillargeon
    -0.49
    зец
    -0.49
    kva
    -0.47
    lankton
    -0.47
    POSITIVE LOGITS
     MainAxisSize
    0.76
    RetentionPolicy
    0.63
    abestanden
    0.59
    angered
    0.52
    complexType
    0.52
     disponibilités
    0.52
    çs
    0.50
     uș
    0.49
    erven
    0.48
     fortunes
    0.48
    Activations Density 0.009%

    No Known Activations