© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 2317
    Prev
    Next
    INDEX
    Explanations

    instances of judicial errors and issues related to legal discretion

    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
    ]>=
    -0.71
    UrlResolution
    -0.65
    ]='\
    -0.65
    "])
    
    -0.65
     confronti
    -0.64
    ]=-
    -0.63
    )||
    -0.62
    '}>
    -0.59
    ]<=
    -0.59
    ratulations
    -0.58
    POSITIVE LOGITS
     erred
    0.74
    Kariera
    0.57
     discretion
    0.56
     teatr
    0.55
     theaters
    0.54
     Auk
    0.53
    anggaran
    0.52
     חיצוניים
    0.51
    醐
    0.51
     Boven
    0.50
    Activations Density 0.025%

    No Known Activations