© 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. 22-RES-MATRYOSHKA-DC
    7. 3155
    Prev
    Next
    INDEX
    Explanations

    words associated with improvements in health and the environment

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     esternos
    -0.53
    انجليز
    -0.47
    })()
    -0.46
    adaş
    -0.46
    satunya
    -0.46
     Stub
    -0.45
     Geduld
    -0.44
    νει
    -0.44
    DeleteBehavior
    -0.43
     AssemblyCulture
    -0.43
    POSITIVE LOGITS
     benefits
    3.05
     benefit
    2.94
    benefit
    2.64
    benefits
    2.64
     Benefits
    2.61
    Benefit
    2.55
     Benefit
    2.52
    Benefits
    2.48
     BENEFITS
    2.44
     advantages
    2.31
    Activations Density 0.964%

    No Known Activations