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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19205
    Prev
    Next
    INDEX
    Explanations

    academic and research-related terminology, specifically those indicating the purpose or nature of studies or articles

    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
     AssemblyVersion
    -0.77
    '])){
    -0.77
     Numerade
    -0.70
    ']));
    -0.68
    "]));
    -0.66
    "])){
    -0.66
     defaultstate
    -0.64
    发表于
    -0.63
    +#+
    -0.60
    '])){
    -0.60
    POSITIVE LOGITS
    InitVars
    0.73
    ngilizce
    0.48
    PropertyChanging
    0.46
    ısında
    0.46
     لينك
    0.45
    DispatchToProps
    0.45
     given
    0.44
    ändig
    0.44
     poss
    0.43
    HttpEntity
    0.42
    Activations Density 0.044%

    No Known Activations