© 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. 1148
    Prev
    Next
    INDEX
    Explanations

    legal jargon related to sentencing guidelines and judicial departures from them

    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
    +#+
    -0.62
    setContentView
    -0.60
     indictment
    -0.59
    RUnlock
    -0.59
     Trials
    -0.59
    Trials
    -0.59
     trials
    -0.58
    criminate
    -0.57
    trials
    -0.57
    trial
    -0.57
    POSITIVE LOGITS
     aggravating
    0.63
     guideline
    0.61
     calculations
    0.60
    kháu
    0.59
     calculation
    0.57
     Sent
    0.56
     Guideline
    0.56
     calculating
    0.55
     calcul
    0.54
     recommend
    0.54
    Activations Density 0.349%

    No Known Activations