© 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. 3-RES-MATRYOSHKA-DC
    7. 2
    Prev
    Next
    INDEX
    Explanations

    words like "actually" "even', "also", "again," and "then"

    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
     Tuc
    -0.69
    変わる
    -0.68
     Pico
    -0.66
     fermés
    -0.66
     Sarg
    -0.65
     Kula
    -0.64
     fights
    -0.63
    わかった
    -0.63
    合わない
    -0.63
    戦う
    -0.61
    POSITIVE LOGITS
     also
    1.55
     ALSO
    1.23
     actually
    1.14
     still
    1.13
     simply
    1.13
     really
    1.12
    theless
    1.12
    ALSO
    1.10
     only
    1.09
     just
    1.09
    Activations Density 5.626%

    No Known Activations