© 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. 1739
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially relating to package imports, function definitions, and copyright notices.

    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
    {{/
    -0.71
    "])){
    -0.68
     propOrder
    -0.64
    '])){
    -0.64
    ])){
    -0.63
    interopRequire
    -0.62
    ']->
    -0.60
    ReusableCell
    -0.60
    '],$
    -0.59
    SequentialGroup
    -0.58
    POSITIVE LOGITS
    protoimpl
    0.67
     func
    0.64
     :=
    0.62
    uintptr
    0.59
    go
    0.57
     rune
    0.56
     Stringer
    0.56
     nil
    0.56
     Fiber
    0.55
    rune
    0.55
    Activations Density 2.523%

    No Known Activations