© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5450
    Prev
    Next
    INDEX
    Explanations

    references to self or self-related constructs

    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
     themselves
    -1.98
    themselves
    -1.91
     himself
    -1.89
     herself
    -1.84
     ourselves
    -1.81
    itself
    -1.80
    himself
    -1.77
     itself
    -1.75
     yourselves
    -1.66
     yourself
    -1.61
    POSITIVE LOGITS
     self
    2.53
     Self
    2.22
    Self
    1.95
     SELF
    1.91
    self
    1.45
    SELF
    1.41
     Selbst
    1.35
    Selbst
    0.93
     sel
    0.84
     само
    0.83
    Activations Density 0.046%

    No Known Activations