© 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. 19364
    Prev
    Next
    INDEX
    Explanations

    mathematical or numerical notation

    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
    enumi
    -0.87
     AssemblyCulture
    -0.81
    verifyException
    -0.77
    ESTRE
    -0.75
    elemField
    -0.73
    FunctionFlags
    -0.70
    uxxxx
    -0.70
    tvguidetime
    -0.70
    MockBean
    -0.69
    ValueStyle
    -0.69
    POSITIVE LOGITS
    1
    0.74
    ☝
    0.60
    ViewFeatures
    0.59
     száz
    0.58
     ১
    0.58
    ONE
    0.57
    quic
    0.56
     unity
    0.55
    AspNet
    0.54
     XI
    0.54
    Activations Density 0.306%

    No Known Activations