© 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. 20532
    Prev
    Next
    INDEX
    Explanations

    technical references related to chemical or physical measurements

    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
    OGND
    -0.79
    ">//
    -0.77
    CloseOperation
    -0.77
    LookAnd
    -0.76
    /*++
    -0.69
    /~
    -0.67
    قایناق‌لار
    -0.67
     PagesJaunes
    -0.67
    nonatomic
    -0.64
    دانشنامهٔ
    -0.63
    POSITIVE LOGITS
    Predecesor
    0.56
     tapaht
    0.48
     vastaan
    0.44
     huom
    0.41
     EventEmitter
    0.41
     podio
    0.41
     Optimis
    0.40
     Adicion
    0.39
     juventud
    0.39
     beträgt
    0.38
    Activations Density 0.039%

    No Known Activations