© 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. 5869
    Prev
    Next
    INDEX
    Explanations

    references to making donations or contributions

    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
    uminense
    -0.75
    xffffff
    -0.63
    atshirt
    -0.62
    ibrill
    -0.61
     itſelf
    -0.61
    URLException
    -0.60
     PFA
    -0.59
     mourir
    -0.59
    xFFFFFF
    -0.59
    phosa
    -0.59
    POSITIVE LOGITS
    principalTable
    0.68
    awtextra
    0.66
    expandindo
    0.61
     <<<<<<<<<<<<<<
    0.55
    >({
    0.55
    MigrationBuilder
    0.54
     '{@
    0.54
    LookAnd
    0.51
    __(/*!
    0.50
     Chwiliwch
    0.47
    Activations Density 0.527%

    No Known Activations