© 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. 18402
    Prev
    Next
    INDEX
    Explanations

    instances of the word "colon" and related morphological variations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Hend
    -0.74
     MCM
    -0.73
     Danilo
    -0.73
     Vite
    -0.71
     Duan
    -0.70
     aspar
    -0.69
     Argos
    -0.68
     Bute
    -0.68
     Cots
    -0.68
    ambung
    -0.67
    POSITIVE LOGITS
    colon
    1.34
     colon
    1.30
     Colon
    1.27
    Colon
    1.18
    ReusableCell
    0.89
     COLON
    0.86
     colonization
    0.84
    COLON
    0.82
     colonists
    0.78
    brushes
    0.72
    Activations Density 0.006%

    No Known Activations