© 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. 32443
    Prev
    Next
    INDEX
    Explanations

    terms associated with genetic and chromosomal analysis

    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
     local
    -0.51
     neighborhood
    -0.50
     localizada
    -0.50
    fürst
    -0.50
     defaultstate
    -0.50
    enares
    -0.50
     loc
    -0.49
     vicin
    -0.49
     location
    -0.47
    begriff
    -0.47
    POSITIVE LOGITS
    енча
    0.66
     diploid
    0.66
    tinyos
    0.65
    uplo
    0.65
    zygous
    0.64
     الاطلاع
    0.63
    脚注の使い方
    0.63
    intios
    0.63
     disambiguazione
    0.63
     haplo
    0.63
    Activations Density 0.022%

    No Known Activations