© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 328
    Prev
    Next
    INDEX
    Explanations

    legal language related to sentencing

    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.22.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.22.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
    mybatisplus
    -0.60
    VERTISING
    -0.52
     Auvergne
    -0.49
     lă
    -0.48
    blik
    -0.46
     dinámico
    -0.45
    jsonp
    -0.44
    اسة
    -0.43
     사업
    -0.43
     createContext
    -0.43
    POSITIVE LOGITS
     sentencing
    1.39
     sentenced
    1.38
     prison
    1.38
     convicted
    1.33
     jail
    1.33
     convict
    1.27
     criminal
    1.25
     incarceration
    1.24
     sentence
    1.24
     imprisonment
    1.19
    Activations Density 4.150%

    No Known Activations