© 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. 10152
    Prev
    Next
    INDEX
    Explanations

    references to abundance or the quantity of something

    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
     Crocker
    -0.73
     syno
    -0.73
     Woodrow
    -0.71
     ModelExpression
    -0.70
     Rites
    -0.69
     Mep
    -0.68
     Caw
    -0.68
     nicio
    -0.67
     talons
    -0.66
     Мексичка
    -0.65
    POSITIVE LOGITS
     abundance
    1.19
    abundance
    1.19
     Abundance
    1.16
     Abund
    1.16
     abundances
    1.16
    Abund
    1.13
    abund
    1.02
     abund
    1.01
     abond
    0.94
     abundant
    0.79
    Activations Density 0.008%

    No Known Activations