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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4002
    Prev
    Next
    INDEX
    Explanations

    programming and technical concepts related to data structures and JSON-like objects

    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
     cauſe
    -0.56
     caufe
    -0.56
    creativecommons
    -0.56
    memoized
    -0.55
     chofe
    -0.54
     fissure
    -0.54
     whoſe
    -0.54
    wsgi
    -0.53
     ſta
    -0.53
    writeFieldEnd
    -0.52
    POSITIVE LOGITS
    ExtendWith
    0.65
     nahilalakip
    0.52
     autorytatywna
    0.50
    WarningLevel
    0.50
    LookAnd
    0.50
    rrggbb
    0.49
     gynhyrchwyd
    0.47
    RunWith
    0.47
    وحة
    0.47
     cherchés
    0.44
    Activations Density 2.301%

    No Known Activations