© 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. 9418
    Prev
    Next
    INDEX
    Explanations

    references to specific mathematical constructs and notations

    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
    0
    -0.54
    5
    -0.49
    2
    -0.49
     correctes
    -0.46
    get
    -0.45
    1
    -0.45
     zase
    -0.43
    idan
    -0.42
     Catto
    -0.42
    いい
    -0.42
    POSITIVE LOGITS
    ConstraintMaker
    0.96
    DockStyle
    0.90
     ujednoznacz
    0.82
     newBuilder
    0.81
     ddelweddau
    0.79
     ModelExpression
    0.78
    出版年
    0.76
    ########.
    0.73
    AndEndTag
    0.73
     חיצוניים
    0.71
    Activations Density 0.013%

    No Known Activations