© 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. 2886
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or mention of someone

    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
    everyone
    -1.37
     anyone
    -1.35
     everyone
    -1.34
     everybody
    -1.31
    everybody
    -1.31
     Everybody
    -1.28
     anybody
    -1.27
    anyone
    -1.27
     Everyone
    -1.25
    Everyone
    -1.24
    POSITIVE LOGITS
     something
    2.19
    something
    2.14
    Something
    2.05
     Something
    2.02
     SOMETHING
    1.64
     quelque
    1.34
     algo
    1.32
     somethin
    1.32
     somewhere
    1.20
     något
    1.19
    Activations Density 0.032%

    No Known Activations