© 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. 2-RES-MATRYOSHKA-DC
    7. 6450
    Prev
    Next
    INDEX
    Explanations

    references to the self object within code snippets

    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
    itself
    -1.59
     itself
    -1.48
     himself
    -1.45
    himself
    -1.45
    themselves
    -1.44
     Itself
    -1.44
     themselves
    -1.38
     herself
    -1.36
     yourself
    -1.24
    herself
    -1.17
    POSITIVE LOGITS
    self
    2.08
     self
    1.67
     Self
    1.52
    Self
    1.43
     SELF
    1.16
    SELF
    1.01
    的自
    0.85
     Selbst
    0.81
    自
    0.67
    eafter
    0.65
    Activations Density 0.028%

    No Known Activations