© 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. 19381
    Prev
    Next
    INDEX
    Explanations

    references to specific articles or sections of a text

    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
     pleaſure
    -0.78
     houſe
    -0.73
     ſaid
    -0.71
     purpoſe
    -0.69
     raiſ
    -0.69
     greateſt
    -0.68
     ſtate
    -0.68
     leaſt
    -0.68
    webElementXpaths
    -0.67
     becauſe
    -0.66
    POSITIVE LOGITS
    かわらず
    0.78
    ibouti
    0.75
    sinon
    0.69
    bewerken
    0.68
    nought
    0.67
    はじめに
    0.66
     đình
    0.66
    ftrag
    0.66
    DockStyle
    0.64
     betweenstory
    0.62
    Activations Density 0.019%

    No Known Activations