© 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. 15065
    Prev
    Next
    INDEX
    Explanations

    references to levels and quantifications, particularly in relation to legal or procedural arguments

    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
    Rujuakan
    -0.75
     okuyayım
    -0.69
    Personensuche
    -0.69
     سكانية
    -0.69
    ConstraintMaker
    -0.68
     CommonModule
    -0.67
     AppComponent
    -0.66
    principalColumn
    -0.66
     चीज़ों
    -0.65
    DeleteBehavior
    -0.64
    POSITIVE LOGITS
    NOPQRST
    0.63
     khuy
    0.49
    PhysRevD
    0.48
     luật
    0.47
    결
    0.47
    fru
    0.47
     tools
    0.46
    ṛ
    0.44
     Chuk
    0.44
    ahara
    0.43
    Activations Density 0.021%

    No Known Activations