© 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. 8732
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to criminal convictions and charges

    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
     Mär
    -0.54
    atr
    -0.52
    urangi
    -0.51
    spre
    -0.50
    וויק
    -0.50
    Panamoan
    -0.50
     disponibilités
    -0.50
     existing
    -0.49
    Existing
    -0.49
     incarcer
    -0.49
    POSITIVE LOGITS
    toThrow
    0.80
    findpost
    0.69
    complexType
    0.67
     Kishi
    0.66
     gäller
    0.64
     GenerationType
    0.64
    />";
    0.64
     äta
    0.64
     flesta
    0.61
     Bourke
    0.60
    Activations Density 0.017%

    No Known Activations