© 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. 16711
    Prev
    Next
    INDEX
    Explanations

    characters or elements related to fictional narratives and their attributes

    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
    AndEndTag
    -0.99
     AssemblyCulture
    -0.98
     &___
    -0.92
    contentLoaded
    -0.90
     للاسماء
    -0.90
    +#+#
    -0.88
    Gambas
    -0.79
    رشف
    -0.78
    :✨
    -0.76
     الحره
    -0.76
    POSITIVE LOGITS
    ????????????????
    0.43
     znaczy
    0.42
    Longrightarrow
    0.41
    nog
    0.40
     penta
    0.40
    målet
    0.40
     contribu
    0.39
     المنام
    0.38
    ositol
    0.37
    Contrary
    0.36
    Activations Density 0.087%

    No Known Activations