© 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. 20193
    Prev
    Next
    INDEX
    Explanations

    specific legal terms and their relevance in the context of agreements and obligations

    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
     ſta
    -0.66
    AddWithValue
    -0.64
     Conſ
    -0.63
     houſe
    -0.58
     ſtate
    -0.57
     Normdatei
    -0.52
     tabernacle
    -0.52
     viſ
    -0.51
    municipi
    -0.51
     coupable
    -0.50
    POSITIVE LOGITS
    AndEndTag
    0.74
    libft
    0.70
    CompleteListener
    0.65
    adaptiveStyles
    0.63
    expandindo
    0.59
    Personendaten
    0.59
    AsUp
    0.59
    providedIn
    0.58
    uzzi
    0.57
    InvalidProtocol
    0.57
    Activations Density 0.284%

    No Known Activations