© 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. 23506
    Prev
    Next
    INDEX
    Explanations

    information related to accounts, services, and purchasing details

    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
     would
    -0.41
    UnusedPrivate
    -0.41
    بيرة
    -0.38
    .
    -0.37
    swal
    -0.36
     am
    -0.36
     extensive
    -0.36
     provide
    -0.35
    段
    -0.35
     ofrecer
    -0.35
    POSITIVE LOGITS
    Tikang
    0.79
    مقاله
    0.77
    ]--;
    0.75
    XmlAccessType
    0.74
    +#+
    0.73
    elemField
    0.72
    saraba
    0.71
    MLLoader
    0.71
    InputTagHelper
    0.71
    __':
    0.71
    Activations Density 0.112%

    No Known Activations