© 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. 15871
    Prev
    Next
    INDEX
    Explanations

    words related to adaptation and changes in response to environments

    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
     Brou
    -0.69
     very
    -0.66
     “
    -0.62
     result
    -0.60
      
    -0.60
     post
    -0.59
     vesti
    -0.59
    űr
    -0.59
     Whitney
    -0.58
    ه
    -0.57
    POSITIVE LOGITS
     Adapt
    1.42
     adapted
    1.33
     adapts
    1.33
     adapting
    1.30
     Adaptation
    1.27
     adaptability
    1.24
     adaptations
    1.22
     adaptable
    1.21
    adapted
    1.21
     adaptor
    1.20
    Activations Density 0.007%

    No Known Activations