© 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. 6295
    Prev
    Next
    INDEX
    Explanations

    references to people leaving or departing

    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
     left
    -1.35
     Left
    -1.25
    Left
    -1.16
     LEFT
    -1.12
    left
    -1.03
     左
    -1.02
    左
    -1.02
     esquerda
    -1.01
    LEFT
    -0.97
     izquierda
    -0.96
    POSITIVE LOGITS
    leave
    1.77
     leave
    1.77
     leaving
    1.72
    Leave
    1.72
     Leave
    1.68
    leaving
    1.61
     LEAVE
    1.50
     Leaving
    1.42
    Leaving
    1.40
     leaves
    1.38
    Activations Density 0.028%

    No Known Activations