© 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. 7060
    Prev
    Next
    INDEX
    Explanations

    references to humor, friendliness, or positive social interactions

    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
     pleaſure
    -0.82
     viable
    -0.60
     specialise
    -0.60
    ceptable
    -0.60
     viſ
    -0.58
     myſelf
    -0.58
     faſt
    -0.57
     cheaper
    -0.57
     חיצוניים
    -0.57
     enrique
    -0.57
    POSITIVE LOGITS
     shrewd
    0.59
     cautious
    0.59
     whimsical
    0.58
    FailureListener
    0.58
     resolute
    0.57
     preco
    0.57
     nonchal
    0.57
     jovial
    0.56
     sly
    0.54
     exuberant
    0.54
    Activations Density 1.783%

    No Known Activations