© 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. 22162
    Prev
    Next
    INDEX
    Explanations

    elements of an object-oriented programming structure, specifically focusing on class and entity relationships

    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
    ValueStyle
    -0.58
     MediatR
    -0.52
    UpdateCommand
    -0.50
    awtextra
    -0.47
     ControllerBase
    -0.47
    UBE
    -0.45
     sist
    -0.45
    WebMethod
    -0.45
     Bárbara
    -0.45
     este
    -0.44
    POSITIVE LOGITS
    ToMany
    0.95
    WithMany
    0.85
     دیکھیے
    0.73
    OGND
    0.69
    WriteBarrier
    0.69
    SequentialGroup
    0.66
    Ligações
    0.65
     Commencez
    0.63
    Gön
    0.63
    Glej
    0.62
    Activations Density 0.022%

    No Known Activations