© 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. 15462
    Prev
    Next
    INDEX
    Explanations

    corporate legal terminology and concepts, particularly those relating to liability and court proceedings

    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
    =“
    -0.47
    NOPQRST
    -0.47
    versch
    -0.45
     vantaggio
    -0.45
    Жен
    -0.45
    Демо
    -0.43
    GraphicsUnit
    -0.43
    ouds
    -0.43
    twimg
    -0.42
    Rés
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.66
     informée
    0.65
    bitField
    0.64
    #+#
    0.63
     we
    0.62
    initComponents
    0.60
    الحياه
    0.60
     there
    0.58
     surla
    0.56
    MigrationBuilder
    0.55
    Activations Density 0.492%

    No Known Activations