© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30873
    Prev
    Next
    INDEX
    Explanations

    the term "amorphous" in relation to materials

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Diar
    -0.72
     abbey
    -0.69
     Whigs
    -0.67
     Gerr
    -0.66
     McAllister
    -0.65
    long
    -0.63
     Monaghan
    -0.63
     IMAP
    -0.61
     Grosvenor
    -0.60
     Sadie
    -0.59
    POSITIVE LOGITS
    phous
    1.54
    stalline
    1.30
     amorphous
    1.13
     Amor
    0.99
    findpost
    0.98
    Amor
    0.97
    crystalline
    0.87
     ویکی‌پدیا
    0.87
    ValueStyle
    0.81
    WithFormat
    0.80
    Activations Density 0.002%

    No Known Activations