© 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. 24-RES-MATRYOSHKA-DC
    7. 399
    Prev
    Next
    INDEX
    Explanations

    legal terms related to sentencing and offenders

    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.24.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.24.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
    …~
    -0.56
     }}"></
    -0.54
     claimants
    -0.54
     Turnier
    -0.54
     Auvergne
    -0.54
     protoimpl
    -0.53
    SharedDtor
    -0.52
    oltán
    -0.51
    Plaintiff
    -0.51
     directores
    -0.51
    POSITIVE LOGITS
     offenses
    1.02
     crimes
    0.98
     felony
    0.98
     sentencing
    0.93
     offences
    0.91
     sentence
    0.89
     offense
    0.89
     conviction
    0.88
     sentenced
    0.86
     crime
    0.86
    Activations Density 2.957%

    No Known Activations