© 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. 12325
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "PostgreSQL" and related database features

    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
     Shack
    -0.72
    lehre
    -0.70
    Redo
    -0.69
    ButtonModule
    -0.68
     jakarta
    -0.67
    Shack
    -0.66
    dula
    -0.65
    lione
    -0.65
     Jank
    -0.64
    Gabi
    -0.64
    POSITIVE LOGITS
     PG
    1.27
     pg
    1.20
    ########.
    1.03
    PG
    1.00
     PGP
    0.99
     PGC
    0.98
    pg
    0.97
     PostgreSQL
    0.93
    WindowConstants
    0.89
    pgsql
    0.89
    Activations Density 0.010%

    No Known Activations