Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16846
    Prev
    Next
    INDEX
    Explanations

    indicators of statistical significance or results that are not applicable

    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
    abancı
    -0.53
     galería
    -0.51
     contactez
    -0.49
     ***!
    -0.48
     množ
    -0.47
     hiér
    -0.46
    чий
    -0.46
    呼ぶ
    -0.45
     magari
    -0.45
     pronti
    -0.45
    POSITIVE LOGITS
     Baillargeon
    0.64
     propOrder
    0.63
     ModelExpression
    0.59
    mybatisplus
    0.57
     Thế
    0.57
    bibfield
    0.57
    efeated
    0.55
    ĩnh
    0.53
    })));
    0.52
     ClassNotFound
    0.52
    Activations Density 0.006%

    No Known Activations