© 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. 6261
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named David

    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
    ˜
    -1.17
    +#+
    -0.86
     myſelf
    -0.71
     poffe
    -0.69
     Monfieur
    -0.65
     Jefus
    -0.65
    UnknownFieldSet
    -0.64
     uſed
    -0.61
     Diſ
    -0.61
     Hura
    -0.61
    POSITIVE LOGITS
     David
    2.50
    David
    2.41
     david
    1.95
     DAVID
    1.91
    DAVID
    1.90
    david
    1.80
     Davids
    1.49
     Davidson
    0.95
    œ
    0.92
     Dave
    0.90
    Activations Density 0.006%

    No Known Activations