© 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. 26518
    Prev
    Next
    INDEX
    Explanations

    specific symbols or mathematical notation used in equations

    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
     flo
    -0.52
     fla
    -0.49
    fio
    -0.47
     Word
    -0.45
    </strong>
    -0.44
     dise
    -0.44
     zin
    -0.44
    nextLine
    -0.44
    Tham
    -0.44
     AllAfrica
    -0.43
    POSITIVE LOGITS
     Monfieur
    1.20
     myſelf
    1.10
     quæ
    1.07
     himſelf
    1.06
     purpoſe
    1.05
     chofe
    0.98
     themſelves
    0.95
     feroit
    0.94
     itſelf
    0.94
     ainfi
    0.92
    Activations Density 0.005%

    No Known Activations