© 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. 22-RES-MATRYOSHKA-DC
    7. 3186
    Prev
    Next
    INDEX
    Explanations

    passages of legal text that involve lists of factors to be considered

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     createSlice
    -0.51
    تقاوى
    -0.50
    chaun
    -0.50
    Artik
    -0.49
    cstdlib
    -0.49
    IGraphics
    -0.49
     misunderstand
    -0.48
     Abre
    -0.48
     lateinit
    -0.47
    ništ
    -0.47
    POSITIVE LOGITS
     factors
    1.60
     Factors
    1.52
    Factors
    1.50
     factor
    1.48
    factors
    1.43
     Factor
    1.38
    Factor
    1.37
     FACTOR
    1.36
     FACTORS
    1.34
     consideration
    1.34
    Activations Density 0.379%

    No Known Activations