© 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. 3084
    Prev
    Next
    INDEX
    Explanations

    sentences quoting legal findings related to courts or agencies

    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
    zzleHttp
    -0.75
    CloseOperation
    -0.75
    ParallelGroup
    -0.72
     للمعارف
    -0.72
     незавершена
    -0.69
    OGND
    -0.67
     AssemblyCulture
    -0.66
    Hauptartikel
    -0.63
     خارجية
    -0.62
     kasarigan
    -0.62
    POSITIVE LOGITS
    uestamente
    0.60
     Findings
    0.59
     basis
    0.54
     findings
    0.53
     Basis
    0.53
     based
    0.52
    basis
    0.51
     Based
    0.48
     basing
    0.48
     Rely
    0.48
    Activations Density 0.173%

    No Known Activations