© 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. 32071
    Prev
    Next
    INDEX
    Explanations

    specific references to visual elements or structured data within images and figures

    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
     EconPapers
    -0.93
    httphttps
    -0.71
    Datuak
    -0.68
    ClientSize
    -0.67
    mybatisplus
    -0.66
     saites
    -0.65
     kasarigan
    -0.64
    UrlResolution
    -0.62
    EDEFAULT
    -0.62
    elemField
    -0.61
    POSITIVE LOGITS
    DockStyle
    0.49
    havn
    0.48
    hikari
    0.47
     shown
    0.46
     utafiti
    0.44
    ginate
    0.44
    뀜
    0.43
    mannschaft
    0.43
     pictured
    0.41
    ksom
    0.41
    Activations Density 0.141%

    No Known Activations