© 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. 22-RES-MATRYOSHKA-DC
    7. 1795
    Prev
    Next
    INDEX
    Explanations

    words related to programming and configuration

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     doInBackground
    -0.74
    MigrationBuilder
    -0.67
    ViewFeatures
    -0.66
    itemBuilder
    -0.57
    CopyWith
    -0.55
    thâu
    -0.52
    isContained
    -0.51
    findpost
    -0.50
    XtraGrid
    -0.50
     hashCode
    -0.50
    POSITIVE LOGITS
     setting
    1.70
     settings
    1.63
     Setting
    1.51
    設定
    1.37
    Setting
    1.35
     Settings
    1.34
     설정
    1.34
    setting
    1.32
     config
    1.25
    settings
    1.23
    Activations Density 2.070%

    No Known Activations