© 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. 1-RES-MATRYOSHKA-DC
    7. 893
    Prev
    Next
    INDEX
    Explanations

    references to physical or measurable objects

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.76
    tonode
    -0.68
    InputTagHelper
    -0.68
    migrationBuilder
    -0.67
    SequentialGroup
    -0.65
    principalColumn
    -0.64
    MockMvc
    -0.64
    MessageTagHelper
    -0.62
    LayoutPanel
    -0.60
     SqlConnection
    -0.60
    POSITIVE LOGITS
     object
    4.63
    object
    4.09
     Object
    3.88
     objects
    3.88
     Objects
    3.58
     OBJECT
    3.55
    Object
    3.50
    objects
    3.41
    OBJECT
    3.08
    Objects
    3.05
    Activations Density 0.584%

    No Known Activations