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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10859
    Prev
    Next
    INDEX
    Explanations

    instances of the word "judge" and its variations

    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
     kasarigan
    -0.77
    Ecology
    -0.60
    влечения
    -0.58
    ército
    -0.55
    hadiran
    -0.54
     hacks
    -0.53
     Holloway
    -0.53
     Ecology
    -0.52
     décret
    -0.52
    excellents
    -0.52
    POSITIVE LOGITS
     judges
    1.25
     judge
    1.22
    jud
    1.20
     jud
    1.17
     JUD
    1.16
    judge
    1.13
     judging
    1.12
     judged
    1.10
    JUD
    1.09
     Jud
    1.07
    Activations Density 0.009%

    No Known Activations