© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22184
    Prev
    Next
    INDEX
    Explanations

    specific keywords and phrases that indicate contextual references and programming-related concepts

    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
     dAtA
    -1.65
     AssemblyCulture
    -1.16
    دانشنامهٔ
    -1.16
    LookAnd
    -1.12
    setVerticalGroup
    -1.11
     nahilalakip
    -1.10
    StoryboardSegue
    -1.10
    :✨
    -1.09
     AssemblyProduct
    -1.02
    awtextra
    -0.99
    POSITIVE LOGITS
     HFILL
    2.81
    dAtA
    1.59
    iNdEx
    1.09
    tvb
    0.94
     tvb
    0.73
    MarshalTo
    0.62
     sov
    0.58
    }");
    0.57
     });
    0.53
    adamente
    0.48
    Activations Density 0.001%

    No Known Activations