© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26800
    Prev
    Next
    INDEX
    Explanations

    superscript notations in mathematical expressions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     EEA
    -0.91
     Eggers
    -0.87
    writeObject
    -0.84
    borderSide
    -0.84
     Gerber
    -0.79
    Pierre
    -0.77
     Pierre
    -0.74
    dresser
    -0.74
     ModelExpression
    -0.74
     Beek
    -0.73
    POSITIVE LOGITS
    sup
    1.56
    Sup
    1.40
     Sup
    1.36
     sup
    1.19
    SUP
    1.11
     SUP
    1.07
     supr
    1.03
     supre
    0.98
     supra
    0.81
     Sop
    0.73
    Activations Density 0.007%

    No Known Activations