© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1390
    Prev
    Next
    INDEX
    Explanations

    words and phrases in medical texts related to bones or bone health and measurements

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hugo
    -0.56
     blé
    -0.51
    Hugo
    -0.48
     Lein
    -0.46
    textcolor
    -0.45
    Django
    -0.45
    wahati
    -0.43
    acco
    -0.43
    CDCl
    -0.42
    Reyn
    -0.41
    POSITIVE LOGITS
     bone
    1.77
     Bone
    1.59
    Bone
    1.47
     bones
    1.45
    bone
    1.43
     oste
    1.38
     osteoporosis
    1.34
     Oste
    1.34
    BONE
    1.34
     Bones
    1.30
    Activations Density 0.585%

    No Known Activations