© 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. 170
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions of removing or uninstalling software or components

    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
    behaved
    -0.55
    얻
    -0.54
     ✭✭
    -0.54
    rítica
    -0.52
     Metacritic
    -0.52
    ximity
    -0.51
    ially
    -0.50
    ronique
    -0.50
    elux
    -0.50
    styleType
    -0.50
    POSITIVE LOGITS
    掉
    0.99
    DeleteMapping
    0.92
    rmtree
    0.88
     删除
    0.85
     remove
    0.83
    remove
    0.82
     removes
    0.82
    REMOVE
    0.82
     removal
    0.82
    AddTagHelper
    0.82
    Activations Density 3.329%

    No Known Activations