© 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. 2942
    Prev
    Next
    INDEX
    Explanations

    references to conflicts of interest

    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
    Personensuche
    -0.74
    
    -0.74
    OGND
    -0.68
     parlato
    -0.68
    EndContext
    -0.68
     transfieras
    -0.67
     ARMY
    -0.67
    EndProject
    -0.67
    CONF
    -0.66
    gouv
    -0.65
    POSITIVE LOGITS
     conflict
    3.06
     Conflict
    2.86
     conflicts
    2.78
    conflict
    2.78
    Conflict
    2.66
     Conflicts
    2.59
     conflits
    2.16
     conflicto
    2.08
    Conflicts
    2.05
     conflit
    2.02
    Activations Density 0.011%

    No Known Activations