© 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. 846
    Prev
    Next
    INDEX
    Explanations

    references to the user's desire or preference

    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
     attempt
    -1.34
     requests
    -1.29
     attempts
    -1.27
     request
    -1.25
     Attempt
    -1.16
     Request
    -1.14
     attempted
    -1.10
    attempt
    -1.09
     Requests
    -1.09
     requested
    -1.08
    POSITIVE LOGITS
     want
    2.89
    want
    2.41
     Want
    2.38
     WANT
    2.13
    Want
    2.11
     wants
    1.88
    WANT
    1.80
    wants
    1.64
     Wants
    1.59
     wanna
    1.57
    Activations Density 0.046%

    No Known Activations