© 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. 6370
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual, particularly their name

    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
     cauſe
    -0.89
     itſelf
    -0.85
     whoſe
    -0.81
     myſelf
    -0.80
     Eſ
    -0.77
     purpoſe
    -0.77
     ſhould
    -0.75
    addGap
    -0.75
     ſhe
    -0.75
     ſtill
    -0.74
    POSITIVE LOGITS
     Robert
    3.19
    Robert
    2.98
     ROBERT
    2.47
     robert
    2.42
    ROBERT
    2.16
    robert
    2.02
     Roberts
    1.43
     Rober
    1.36
     Роб
    1.35
     Bob
    1.34
    Activations Density 0.011%

    No Known Activations