© 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. 6038
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their attributes

    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
     الرياضيه
    -1.05
     kasarigan
    -0.84
     Teg
    -0.79
     PMP
    -0.74
    +++++
    -0.72
     CreateTagHelper
    -0.70
    minu
    -0.68
    SpringBootTest
    -0.68
    pausal
    -0.68
    pfung
    -0.67
    POSITIVE LOGITS
    td
    1.26
     td
    0.77
     colspan
    0.69
    <td>
    0.67
    CodedInputStream
    0.63
    </td>
    0.62
     Caballero
    0.61
     imageNamed
    0.60
    ؤلاء
    0.59
    hubarb
    0.58
    Activations Density 0.014%

    No Known Activations