© 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. 16568
    Prev
    Next
    INDEX
    Explanations

    elements of mathematical 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
     AssemblyCulture
    -0.76
    SequentialGroup
    -0.64
    存于互联网档案馆
    -0.61
    +#+#
    -0.61
    gulation
    -0.59
    FunctionFlags
    -0.58
    DebuggerStep
    -0.58
    ammlung
    -0.57
    StructEnd
    -0.57
    脚注の使い方
    -0.56
    POSITIVE LOGITS
    jeeling
    0.63
    oa̍t
    0.61
    HasColumnType
    0.58
    WriteBarrier
    0.56
     dAtA
    0.56
     grà
    0.56
    ChildIndex
    0.56
    titleMargin
    0.54
    Попис
    0.53
     Arti
    0.52
    Activations Density 0.066%

    No Known Activations