© 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. 23297
    Prev
    Next
    INDEX
    Explanations

    indicators of legal arguments or evidence presented in a judicial context

    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
    </code>
    -0.52
    ьер
    -0.50
     [*]
    -0.48
    suff
    -0.47
     vendar
    -0.46
    roppo
    -0.45
    YV
    -0.45
    jmniej
    -0.45
     getContent
    -0.44
    irp
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    0.95
     JpaRepository
    0.88
    تقاوى
    0.79
     виправивши
    0.74
    Personendaten
    0.69
    Personensuche
    0.67
     <<<<<<<<<<<<<<
    0.66
    NewUrlParser
    0.66
     estekak
    0.64
    chartInstance
    0.63
    Activations Density 0.013%

    No Known Activations