© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to finality and conclusion in discussions

    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
     Racine
    -0.61
    D
    -0.60
     fermés
    -0.60
    Ser
    -0.59
     aeration
    -0.59
    IC
    -0.58
     setae
    -0.58
     élevées
    -0.57
    A
    -0.57
     rapides
    -0.57
    POSITIVE LOGITS
    theless
    1.13
    ingly
    0.96
    handedly
    0.94
     autorytatywna
    0.92
    BufferException
    0.91
    BibitemShut
    0.89
     оригіналу
    0.89
    sively
    0.88
    AsUp
    0.88
    arily
    0.86
    Activations Density 4.808%

    No Known Activations