© 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. 24872
    Prev
    Next
    INDEX
    Explanations

    parameter names in a system configuration 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
    دانشنامهٔ
    -0.89
     صوتيه
    -0.79
    featureID
    -0.77
     Wikimedijinoj
    -0.74
    Hentet
    -0.72
    MessageOf
    -0.71
    expandindo
    -0.70
    SharedDtor
    -0.69
    endphp
    -0.68
     Jefus
    -0.68
    POSITIVE LOGITS
     following
    0.54
    határoz
    0.54
    躇
    0.53
     II
    0.51
     out
    0.50
    tagHelperRunner
    0.50
    dom
    0.50
    topic
    0.50
    cstring
    0.49
     Although
    0.48
    Activations Density 0.001%

    No Known Activations