© 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. 2-RES-MATRYOSHKA-DC
    7. 6749
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fight" and its variations

    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
    tonode
    -0.89
    GEBURTSDATUM
    -0.87
     ExecuteAsync
    -0.75
     jScrollPane
    -0.75
    ::::::::
    -0.71
     kasarigan
    -0.71
     ब्रेकडाउन
    -0.70
    SharedDtor
    -0.70
    WithIOException
    -0.68
    InputBorder
    -0.68
    POSITIVE LOGITS
     fight
    3.11
    fight
    2.84
     Fight
    2.70
     fights
    2.64
     FIGHT
    2.56
    Fight
    2.53
     fighting
    2.50
     fought
    2.34
    FIGHT
    2.34
    fights
    2.31
    Activations Density 0.043%

    No Known Activations