© 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. 12260
    Prev
    Next
    INDEX
    Explanations

    references to counterparts or comparisons between similar entities

    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
     },
    -0.65
    schra
    -0.65
    .'</
    -0.64
    }{%
    -0.61
    icycles
    -0.61
    imental
    -0.60
     sobran
    -0.59
    TextBoxColumn
    -0.58
    ##
    -0.58
     }</
    -0.57
    POSITIVE LOGITS
     counterparts
    1.23
     counterpart
    1.21
     successor
    0.85
     equivalents
    0.83
     successors
    0.78
     predecess
    0.77
     companion
    0.71
    part
    0.69
    +#+
    0.69
     predecessor
    0.68
    Activations Density 0.008%

    No Known Activations