© 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. 24560
    Prev
    Next
    INDEX
    Explanations

    sections marked with a heading or delimiter

    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
     Bates
    -0.81
     المعيارى
    -0.72
     DES
    -0.71
     Poole
    -0.68
    DES
    -0.66
    SpringBoot
    -0.66
    omsday
    -0.65
     Goa
    -0.65
     "',
    -0.64
    ",
    -0.64
    POSITIVE LOGITS
     ####
    0.89
    theless
    0.82
    例句
    0.81
    ####
    0.81
    PerformLayout
    0.76
     Vainqueur
    0.71
     Ogil
    0.71
    tagHelperRunner
    0.71
     بيها
    0.69
     wigs
    0.68
    Activations Density 0.002%

    No Known Activations