© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14883
    Prev
    Next
    INDEX
    Explanations

    code-related elements and structures including data types, variables, and functions in programming

    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
    Negative Logits
    XMLSchema
    -0.92
     HasFactory
    -0.86
    AsUp
    -0.84
     SafeMath
    -0.82
    IVEREF
    -0.82
    HideFlags
    -0.81
     defStyle
    -0.75
    Personendaten
    -0.73
    LabelTagHelper
    -0.71
    FileDescriptor
    -0.71
    POSITIVE LOGITS
    "]);
    0.44
    sikker
    0.44
     للاسماء
    0.43
    ()]);
    0.42
    "]];
    0.40
     performance
    0.39
     }}$}
    0.39
    andag
    0.38
     exercise
    0.37
     určit
    0.36
    Activations Density 0.053%

    No Known Activations