© 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. 13985
    Prev
    Next
    INDEX
    Explanations

    references to scientific articles or studies, particularly those involving data and classification in bioinformatics

    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
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.97
    setVerticalGroup
    -0.77
    awtextra
    -0.76
    DockStyle
    -0.75
    argout
    -0.74
     houſe
    -0.73
     pleaſure
    -0.67
     Houſe
    -0.64
     createContext
    -0.62
    AccessorTable
    -0.60
    POSITIVE LOGITS
    DebuggerNonUser
    0.52
     دیکھیے
    0.48
    ukun
    0.47
    ൂ
    0.46
    どき
    0.43
    oare
    0.42
    isDefault
    0.42
    runOnUiThread
    0.42
     kê
    0.41
    tim
    0.41
    Activations Density 0.006%

    No Known Activations