© 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. 18-RES-MATRYOSHKA-DC
    7. 712
    Prev
    Next
    INDEX
    Explanations

    text from legal documents, specifically names of judges and legal terminology.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    󠁢
    -0.60
    حوال
    -0.59
     feuille
    -0.54
    losures
    -0.54
    enumi
    -0.53
    preventDefault
    -0.50
     battre
    -0.49
    IfNeeded
    -0.49
    agaimana
    -0.49
    trunc
    -0.48
    POSITIVE LOGITS
     dissenting
    0.72
     transfieras
    0.72
     CURIAM
    0.68
    NameInMap
    0.65
    LookAnd
    0.63
    InjectAttribute
    0.62
    XmlAccessorType
    0.62
    +#+#
    0.60
    IndentedString
    0.59
     يتيمه
    0.57
    Activations Density 0.344%

    No Known Activations