© 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. 3831
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific instruments and measurement 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
    moveToFirst
    -0.71
     propOrder
    -0.57
    ctio
    -0.54
    ací
    -0.52
     تكبرها
    -0.51
     bambina
    -0.49
    totic
    -0.48
     Chủ
    -0.48
    calloc
    -0.48
    漬け
    -0.47
    POSITIVE LOGITS
    migrationBuilder
    0.78
    Errorf
    0.71
     Coh
    0.71
    ECO
    0.69
     coe
    0.65
     שוליים
    0.65
     خارجية
    0.65
    jgl
    0.64
     aco
    0.64
     CO
    0.61
    Activations Density 0.270%

    No Known Activations