© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3818
    Prev
    Next
    INDEX
    Explanations

    genes and mutations associated with diseases

    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
     &___
    -0.62
    ագրություններ
    -0.61
     esboço
    -0.57
    /**
    -0.55
    ksis
    -0.54
    OptionsMenu
    -0.54
    DialogComponent
    -0.54
    editForm
    -0.53
    iosamente
    -0.53
    merce
    -0.52
    POSITIVE LOGITS
    etc
    0.64
    GeneratedCode
    0.59
     etc
    0.52
    ?,?,
    0.52
     Bala
    0.52
    RenderAtEndOf
    0.52
    ilo
    0.50
     kati
    0.50
     Theſe
    0.50
    internalType
    0.48
    Activations Density 0.491%

    No Known Activations