© 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. 20179
    Prev
    Next
    INDEX
    Explanations

    references to the Veterans Administration (VA)

    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
     migrator
    -0.89
    FieldDescriptor
    -0.85
    terase
    -0.84
    ctose
    -0.82
    éter
    -0.82
    Ander
    -0.81
    ">//
    -0.81
     šķ
    -0.76
     NEL
    -0.75
     Ander
    -0.75
    POSITIVE LOGITS
     VA
    1.48
    GINIA
    1.36
     Va
    1.33
     Virginia
    1.24
    VA
    1.20
    Va
    1.11
    Virginia
    1.11
     va
    1.06
     virginia
    1.06
     Vaid
    1.06
    Activations Density 0.025%

    No Known Activations