© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 404
    Prev
    Next
    INDEX
    Explanations

    adverbs

    oai_token-act-pair · gemini-2.0-flash
    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
     Adapt
    -0.70
     Wulf
    -0.69
     ripar
    -0.68
     ADAPT
    -0.66
    vara
    -0.66
     manche
    -0.65
     hals
    -0.63
    わかった
    -0.63
    Exc
    -0.63
    ό
    -0.63
    POSITIVE LOGITS
    denly
    1.34
    ently
    1.34
    sively
    1.23
    ligently
    1.22
    tically
    1.20
    cerely
    1.20
    atically
    1.20
    mically
    1.20
    ously
    1.16
    operatively
    1.16
    Activations Density 1.823%

    No Known Activations