© 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. 617
    Prev
    Next
    INDEX
    Explanations

    references to bone and bone-related materials or structures

    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
    Havolalar
    -0.61
     AssemblyCulture
    -0.58
     Bassi
    -0.58
     Guiana
    -0.57
     cú
    -0.55
     AssemblyVersion
    -0.54
     Rana
    -0.54
    StoryboardSegue
    -0.52
    Географи
    -0.51
    ecd
    -0.51
    POSITIVE LOGITS
     bone
    3.97
     Bone
    3.63
    Bone
    3.42
    bone
    3.41
     bones
    3.34
    BONE
    3.00
    bones
    2.98
     Bones
    2.94
    Bones
    2.69
     Knochen
    2.38
    Activations Density 0.530%

    No Known Activations