© 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. 1-RES-MATRYOSHKA-DC
    7. 1258
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis on provided information

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     provided
    -1.66
    provided
    -1.64
    Provided
    -1.50
     Provided
    -1.47
     PROVIDED
    -1.41
     provision
    -1.26
     Provision
    -1.16
    provision
    -1.15
    PROVID
    -1.13
     Provider
    -1.08
    POSITIVE LOGITS
     give
    3.11
     Give
    3.06
    give
    3.05
    Give
    3.00
     giving
    2.80
     GIVE
    2.75
     Giving
    2.67
    Giving
    2.67
     gives
    2.64
    giving
    2.61
    Activations Density 0.169%

    No Known Activations