© 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. 6883
    Prev
    Next
    INDEX
    Explanations

    references to desired control or target parameters

    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
     reck
    -0.61
    RenderAtEndOf
    -0.60
     Notwithstanding
    -0.60
    //
    -0.59
     reckon
    -0.59
    ump
    -0.57
     Witherspoon
    -0.57
    っこう
    -0.56
     hefyd
    -0.54
     Noodle
    -0.54
    POSITIVE LOGITS
     desired
    2.44
    desired
    2.33
     Desired
    2.25
    Desired
    1.95
     desirable
    1.86
     desire
    1.39
     desires
    1.38
     desirability
    1.36
     deseado
    1.36
     desir
    1.34
    Activations Density 0.014%

    No Known Activations