© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8447
    Prev
    Next
    INDEX
    Explanations

    technical terminology and structures related to programming or data protocols

    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
     sv
    -0.42
    OLOGÍA
    -0.40
    prakti
    -0.40
     gele
    -0.40
    blad
    -0.39
    lacht
    -0.38
     suy
    -0.38
    etsu
    -0.38
    
    -0.38
     Land
    -0.37
    POSITIVE LOGITS
    contentLoaded
    0.76
    IndentedString
    0.75
    IsContent
    0.74
    ioutil
    0.73
    Rujuakan
    0.69
    protoimpl
    0.68
     بيها
    0.68
    ScopeManager
    0.65
    endphp
    0.65
     sztuki
    0.63
    Activations Density 0.658%

    No Known Activations