© 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. 25432
    Prev
    Next
    INDEX
    Explanations

    various forms and characteristics of aqueous extracts from plants

    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
    StructEnd
    -0.88
    TemporalType
    -0.71
     distanciation
    -0.70
    SharedCtor
    -0.69
    ectady
    -0.66
     daqui
    -0.66
    ThroughAttribute
    -0.65
     للمعارف
    -0.65
    makeConstraints
    -0.63
     intptr
    -0.63
    POSITIVE LOGITS
    eavour
    0.65
     moder
    0.47
    irected
    0.47
    BadRequest
    0.47
     ProgressBar
    0.45
    eavor
    0.45
    __()
    0.44
    asty
    0.43
    moder
    0.43
    aksanaan
    0.43
    Activations Density 0.043%

    No Known Activations