© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1149
    Prev
    Next
    INDEX
    Explanations

    structural and procedural elements in a scientific or analytical 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
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.45
     whiteColor
    -0.44
    leyebilirsiniz
    -0.43
    另
    -0.43
    <eos>
    -0.42
    Chham
    -0.42
    oulli
    -0.40
    рит
    -0.40
    unif
    -0.40
     trotzdem
    -0.39
    POSITIVE LOGITS
    awtextra
    0.88
     Monfieur
    0.84
    principalColumn
    0.81
     Efq
    0.81
     AssemblyCompany
    0.80
    InputBorder
    0.80
     autorytatywna
    0.79
    AndEndTag
    0.78
     myſelf
    0.77
     StatefulWidget
    0.75
    Activations Density 2.580%

    No Known Activations