© 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. 30007
    Prev
    Next
    INDEX
    Explanations

    phrases related to racing achievements and performance metrics

    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
    protoimpl
    -0.85
    UnusedPrivate
    -0.82
    IsMutable
    -0.78
    OGND
    -0.73
     protoimpl
    -0.73
    VersionUID
    -0.72
    AddTagHelper
    -0.70
     ProtoMessage
    -0.68
    UnsafeEnabled
    -0.68
    ChildScrollView
    -0.66
    POSITIVE LOGITS
     max
    0.51
    irnov
    0.50
    max
    0.50
     possible
    0.49
    Max
    0.46
     Max
    0.44
    WriteLine
    0.44
     ever
    0.43
     максима
    0.43
    ριν
    0.43
    Activations Density 0.132%

    No Known Activations