© 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. 16057
    Prev
    Next
    INDEX
    Explanations

    terms related to memory technology and specifications

    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
    StoryboardSegue
    -0.75
    Geografie
    -0.63
    GEBURTSDATUM
    -0.62
    EndInit
    -0.62
    LabelTagHelper
    -0.61
    плом
    -0.59
     combineReducers
    -0.59
    setViewport
    -0.58
     Balo
    -0.57
    UpInside
    -0.57
    POSITIVE LOGITS
     DDR
    1.07
    DDR
    1.02
    ddr
    0.91
     ddr
    0.81
     gynhyrchwyd
    0.76
     DRAM
    0.69
     Picchu
    0.63
     переписи
    0.63
    oflavin
    0.55
    LOAT
    0.53
    Activations Density 0.004%

    No Known Activations