© 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. 3548
    Prev
    Next
    INDEX
    Explanations

    references to the word "Gradle" and associated terms

    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
     Kessel
    -0.83
    beelding
    -0.75
     Hester
    -0.75
     Chwiliwch
    -0.75
    monger
    -0.73
     Phoebe
    -0.72
    omenclature
    -0.72
    feuer
    -0.71
    xase
    -0.71
    principalTable
    -0.70
    POSITIVE LOGITS
     Gra
    1.49
    Gra
    1.45
     Graff
    1.37
     GRA
    1.34
    gra
    1.29
     gra
    1.29
     Gracie
    1.29
     Grayson
    1.11
     Graz
    1.05
    gradle
    1.01
    Activations Density 0.195%

    No Known Activations