© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16196
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "abuse" related to judicial 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
     Wentworth
    -0.79
    
    -0.78
    erom
    -0.70
    __((
    -0.70
    lut
    -0.69
     Vard
    -0.69
     Sut
    -0.68
    (\
    -0.68
     AppComponent
    -0.66
    strictEqual
    -0.66
    POSITIVE LOGITS
    Abuse
    1.12
     Abuse
    1.07
    abuse
    1.01
     abuse
    0.99
     abused
    0.90
    Amicalement
    0.81
     pály
    0.78
    IsMutable
    0.78
    الدراسه
    0.77
     resourceCulture
    0.76
    Activations Density 0.005%

    No Known Activations