© 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. 30870
    Prev
    Next
    INDEX
    Explanations

    instructions and descriptions related to usage or operations of software or systems

    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
     Efq
    -0.91
     houſe
    -0.85
     cauſe
    -0.81
     purpoſe
    -0.80
     fevere
    -0.78
     poffe
    -0.78
     pinulongan
    -0.77
     raiſ
    -0.77
     Reſ
    -0.77
     pleaſure
    -0.77
    POSITIVE LOGITS
    Procedure
    0.66
     Procedure
    0.63
     procedure
    0.63
     simply
    0.55
     PROCEDURE
    0.54
    procedure
    0.53
     Simply
    0.52
    Simply
    0.52
     einfach
    0.51
     procedimento
    0.51
    Activations Density 0.445%

    No Known Activations