© 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. 17099
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their associated properties in a scientific context

    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
     MainAxisSize
    -0.51
     Insel
    -0.46
    岸
    -0.44
    pre
    -0.44
     tore
    -0.44
     gemeenten
    -0.44
    atella
    -0.44
    mo
    -0.43
    jet
    -0.43
    FD
    -0.42
    POSITIVE LOGITS
     lenker
    0.83
    }))
    0.74
     <<<<<<<<<<<<<<
    0.74
     vectorielle
    0.71
    LookAnd
    0.70
    ^(@)
    0.66
    ModelAdmin
    0.66
    NgModule
    0.64
     initComponents
    0.61
     ComVisible
    0.61
    Activations Density 0.032%

    No Known Activations