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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 1548
    Prev
    Next
    INDEX
    Explanations

    information regarding authorship and publication metrics

    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
    JAXB
    -0.62
    IsContent
    -0.59
     aceasta
    -0.54
     oeufs
    -0.52
    낸
    -0.50
    stateParams
    -0.50
     发表于
    -0.49
    tetrahydro
    -0.48
    sizeCache
    -0.47
     său
    -0.47
    POSITIVE LOGITS
     thousands
    0.78
    rungsseite
    0.78
     hundreds
    0.75
     eight
    0.73
     nine
    0.73
     dozen
    0.73
     six
    0.71
     dozens
    0.71
    ########.
    0.71
     الرياضيه
    0.70
    Activations Density 0.826%

    No Known Activations