© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 547
    Prev
    Next
    INDEX
    Explanations

    mentions of "object oriented" and related terms occurring in descriptions about software development

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    addGap
    -0.65
     AssemblyTitle
    -0.63
    GraphicsUnit
    -0.60
     getCount
    -0.58
    efec
    -0.57
    explique
    -0.56
     Helle
    -0.56
    pois
    -0.56
     ſche
    -0.56
    AutoScale
    -0.54
    POSITIVE LOGITS
     objects
    1.10
    objects
    1.06
     obj
    1.05
     Objects
    0.99
     OBJECT
    0.93
     object
    0.91
    WEBPACK
    0.90
    GetObject
    0.88
    ThroughAttribute
    0.85
     objetos
    0.85
    Activations Density 0.191%

    No Known Activations