© 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. 24-RES-MATRYOSHKA-DC
    7. 78
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related words such as family and department

    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.24.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.24.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
    ImageContext
    -1.02
    DockStyle
    -0.81
    ViewFeatures
    -0.80
     Tatsache
    -0.80
    principalTable
    -0.79
    InjectAttribute
    -0.77
    ContentAsync
    -0.75
    DoubleQuotes
    -0.75
     Itself
    -0.72
     voren
    -0.72
    POSITIVE LOGITS
     own
    1.92
    own
    1.07
     efforts
    1.02
     ability
    1.01
     favorite
    0.98
     biggest
    0.94
     beloved
    0.93
     Own
    0.93
     personal
    0.92
     OWN
    0.91
    Activations Density 2.268%

    No Known Activations