© 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. 10795
    Prev
    Next
    INDEX
    Explanations

    phrases related to material composition and structural properties

    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
     MenuView
    -0.70
    InvalidProtocol
    -0.67
    AddHtmlAttribute
    -0.64
    StoryboardSegue
    -0.63
    NOPQRST
    -0.63
    PickerController
    -0.62
     Normdatei
    -0.60
    }".
    -0.60
    icordia
    -0.60
    EndGlobalSection
    -0.60
    POSITIVE LOGITS
     or
    0.94
     Alternatively
    0.81
    Alternatively
    0.79
     arba
    0.71
     или
    0.66
     یا
    0.63
     либо
    0.61
     oppure
    0.60
     ή
    0.59
    或
    0.59
    Activations Density 0.516%

    No Known Activations