© 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. 10657
    Prev
    Next
    INDEX
    Explanations

    terms associated with various applications of technology and their relevance in practical, clinical, industrial, and military contexts

    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
    localPosition
    -0.43
     пло
    -0.40
    实
    -0.40
     β
    -0.39
    帖最后由
    -0.37
     lo
    -0.36
    โล
    -0.36
     visceral
    -0.36
     actual
    -0.36
     Mr
    -0.35
    POSITIVE LOGITS
    MENAFN
    0.79
    expandindo
    0.79
    脚注の使い方
    0.75
    TargetException
    0.74
    ConstraintMaker
    0.72
     >=",
    0.70
    makeText
    0.69
    ngdoc
    0.68
    bootstrapcdn
    0.67
     GenerationType
    0.66
    Activations Density 0.059%

    No Known Activations