© 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. 25380
    Prev
    Next
    INDEX
    Explanations

    terms related to electric and hybrid vehicles and their components

    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
     للاسماء
    -0.77
    ulite
    -0.54
    糊
    -0.50
     diện
    -0.49
    lusconi
    -0.48
    קישורים
    -0.48
    Formazione
    -0.48
    vensko
    -0.48
    kkue
    -0.47
    ator
    -0.47
    POSITIVE LOGITS
    RegressionTest
    0.77
    +#+#
    0.77
    offsetof
    0.70
     "..\..\..\
    0.67
     CanadaChoose
    0.62
    tagHelperRunner
    0.61
     Charging
    0.59
    jago
    0.57
     Equally
    0.57
     EVs
    0.57
    Activations Density 0.005%

    No Known Activations