© 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. 32389
    Prev
    Next
    INDEX
    Explanations

    elements related to environmental or ecological impact

    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
     onView
    -0.60
    beiros
    -0.55
     Alhambra
    -0.52
     متحده
    -0.52
    pertino
    -0.51
    TargetException
    -0.50
    phosa
    -0.50
     miniatur
    -0.49
     tér
    -0.49
     Walking
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.80
    aarrggbb
    0.65
    findpost
    0.65
    DoubleQuotes
    0.65
     airspace
    0.64
    
    0.63
    tvguidetime
    0.62
    VolleyError
    0.62
     VOW
    0.61
     ModelExpression
    0.60
    Activations Density 0.101%

    No Known Activations