© 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. 31927
    Prev
    Next
    INDEX
    Explanations

    attributes related to car specifications and design elements

    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
    Portail
    -0.79
    themselves
    -0.76
     themselves
    -0.72
    ValueStyle
    -0.72
     ourselves
    -0.69
     yourselves
    -0.66
     yourself
    -0.65
     habet
    -0.61
     présentés
    -0.60
     oneself
    -0.60
    POSITIVE LOGITS
    TestingModule
    0.51
     memori
    0.50
    دانشنامهٔ
    0.49
    PreferredItem
    0.48
    ⓧ
    0.48
    GIVEREF
    0.47
    AndroidJUnit
    0.47
    BoxLayout
    0.45
    AutoScale
    0.44
    enchymal
    0.44
    Activations Density 0.054%

    No Known Activations