© 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. 19880
    Prev
    Next
    INDEX
    Explanations

    words describing brightness and vividness

    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
     Huber
    -0.74
    LabelTagHelper
    -0.72
    CrossRef
    -0.70
     ThemeData
    -0.70
    monies
    -0.69
     utafitiHapana
    -0.65
     onData
    -0.64
    lapsingToolbar
    -0.64
     mData
    -0.63
     legger
    -0.63
    POSITIVE LOGITS
     Bright
    1.16
     BRIGHT
    1.08
    Bright
    1.00
    BRIGHT
    0.96
    bright
    0.95
    Brightness
    0.87
     Hove
    0.84
     Brightness
    0.84
     bright
    0.80
    стоин
    0.77
    Activations Density 0.003%

    No Known Activations