© 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. 28726
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arbitrary."

    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
    Conan
    -0.65
     AR
    -0.61
     Conan
    -0.60
    tagext
    -0.60
     Lans
    -0.59
    $[
    -0.56
    nder
    -0.56
    AnchorTagHelper
    -0.56
     Morn
    -0.56
    しく
    -0.55
    POSITIVE LOGITS
     Arbitrary
    1.13
    arbitrary
    1.07
     arbitrarily
    1.00
     arbitrary
    0.97
     arbit
    0.90
    RepeatedField
    0.89
     nahilalakip
    0.79
    arbit
    0.79
     Efq
    0.78
    didSet
    0.78
    Activations Density 0.002%

    No Known Activations