© 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. 270
    Prev
    Next
    INDEX
    Explanations

    references to statistical or analytical results and their implications

    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
    hasMoreElements
    -0.57
     оригіналу
    -0.55
    DropTable
    -0.53
    넷
    -0.52
    .
    -0.51
    KommentareTeilen
    -0.49
     inoltre
    -0.49
     a
    -0.49
     another
    -0.48
    ).
    -0.47
    POSITIVE LOGITS
    bulaire
    0.77
    fromnode
    0.72
    GeneratedCode
    0.71
    ésult
    0.68
    sizeCache
    0.65
    namon
    0.65
    ENEFITS
    0.62
    ftances
    0.62
    RenderAtEndOf
    0.62
    esterday
    0.61
    Activations Density 2.456%

    No Known Activations