© 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. 15976
    Prev
    Next
    INDEX
    Explanations

    phrases indicating funding or support from institutions

    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
    CodeAttribute
    -0.93
     CreateTagHelper
    -0.89
    principalColumn
    -0.88
     Roskov
    -0.81
    webElementXpaths
    -0.80
     initComponents
    -0.79
    новништво
    -0.79
     Signalez
    -0.77
     שוליים
    -0.77
    apimachinery
    -0.74
    POSITIVE LOGITS
    tight
    0.46
    ęcia
    0.46
    Formatting
    0.45
    緩
    0.45
    قق
    0.42
    EMAN
    0.41
    ima
    0.41
     روز
    0.41
    誉
    0.41
    Solids
    0.40
    Activations Density 0.013%

    No Known Activations