© 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. 25443
    Prev
    Next
    INDEX
    Explanations

    the structure and specifications related to positioning elements in a webpage's CSS

    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
    fjspx
    -0.82
     whereof
    -0.76
     resourceCulture
    -0.71
    tagHelperRunner
    -0.69
     Monfieur
    -0.69
    ratulations
    -0.68
    mybatisplus
    -0.66
    UnusedPrivate
    -0.65
    addPreferredGap
    -0.63
     Theſe
    -0.63
    POSITIVE LOGITS
    abestanden
    0.59
    TabIndex
    0.56
    Subview
    0.52
    layer
    0.51
    dessus
    0.48
    zIndex
    0.47
    paksa
    0.46
    Pri
    0.45
    UniformLocation
    0.45
    ʊ
    0.44
    Activations Density 0.006%

    No Known Activations