© 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. 9502
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores and their associated syntax or definitions in a programming context

    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
     Bane
    -0.61
    er
    -0.57
    Ca
    -0.56
    ponen
    -0.56
    wają
    -0.54
     COV
    -0.53
     Nol
    -0.53
    ner
    -0.52
    Clu
    -0.52
    ن
    -0.52
    POSITIVE LOGITS
     gtk
    1.54
    Gtk
    1.49
     Gtk
    1.49
    gtk
    1.39
    GTK
    1.28
     GTK
    1.23
    mybatisplus
    0.88
     iconTwitter
    0.79
     صوتيه
    0.77
    ruptedException
    0.75
    Activations Density 0.001%

    No Known Activations