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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 26488
    Prev
    Next
    INDEX
    Explanations

    references to mathematical operations or expressions involving dimensions or matrix multiplications

    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
     protoimpl
    -0.62
     AssemblyVersion
    -0.59
    esez
    -0.59
    CppMethod
    -0.57
    ConstraintMaker
    -0.56
     commerciale
    -0.55
    complexContent
    -0.54
     виправивши
    -0.54
    IndentedString
    -0.54
    Tembelea
    -0.54
    POSITIVE LOGITS
     gynhyrchwyd
    0.55
    $_['
    0.54
     Naidu
    0.51
     Cl
    0.50
     MonoBehaviour
    0.49
    勅
    0.49
    encodeWith
    0.48
     فريبيس
    0.47
    oneg
    0.47
    朗
    0.47
    Activations Density 0.003%

    No Known Activations