© 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. 838
    Prev
    Next
    INDEX
    Explanations

    legal jargon such as case names, attorneys, and legal roles

    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
    stdc
    -0.64
    mybatisplus
    -0.64
    +#+#
    -0.61
     createSlice
    -0.60
     Inga
    -0.54
    ://$
    -0.53
    馃
    -0.53
     snippetHide
    -0.53
     createStore
    -0.52
    omeness
    -0.50
    POSITIVE LOGITS
     defendant
    1.58
     defendants
    1.54
     Defendant
    1.33
     Defendants
    1.27
     respondent
    1.23
    Defendant
    1.22
     respondents
    1.13
     plaintiff
    1.13
    defendant
    1.13
     Respondent
    1.09
    Activations Density 1.697%

    No Known Activations