© 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. 10987
    Prev
    Next
    INDEX
    Explanations

    CSS properties and transformations related to rotation

    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
    stdarg
    -0.50
    labilir
    -0.50
    grove
    -0.48
     MainAxisSize
    -0.48
    jod
    -0.47
     désolés
    -0.47
    zenten
    -0.46
    atient
    -0.45
    feu
    -0.45
    ofday
    -0.45
    POSITIVE LOGITS
    sizeCache
    0.82
    LookAnd
    0.79
    ISupport
    0.74
    complexContent
    0.70
     kasarigan
    0.68
    NamedQueries
    0.68
    SharedCtor
    0.66
    WithIOException
    0.66
     ویکی‌پدی
    0.63
    FieldBuilder
    0.63
    Activations Density 0.006%

    No Known Activations