© 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. 9558
    Prev
    Next
    INDEX
    Explanations

    programming language constructs or syntax elements, particularly those associated with function definitions and variable assignments

    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
    $_['
    -0.54
     Среди
    -0.49
     carter
    -0.47
    illants
    -0.47
     lo
    -0.46
    atis
    -0.45
    seende
    -0.44
    interpolate
    -0.43
     milieu
    -0.43
    InitVars
    -0.43
    POSITIVE LOGITS
    DockStyle
    0.88
    MigrationBuilder
    0.88
     contextLoads
    0.71
    VersionUID
    0.70
    Rujuakan
    0.66
     MenuView
    0.66
    Carriera
    0.65
    raszamy
    0.64
    TextWatcher
    0.62
     ContentValues
    0.60
    Activations Density 0.192%

    No Known Activations