© 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. 0-RES-MATRYOSHKA-DC
    7. 12062
    Prev
    Next
    INDEX
    Explanations

    references to the concept of personal preference or individual choice

    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
     Preferences
    -1.04
    preferences
    -1.01
     preferences
    -0.88
    Preferences
    -0.80
     Prefer
    -0.69
     Pref
    -0.66
    Prefer
    -0.64
     PREF
    -0.63
    PREF
    -0.60
    Pren
    -0.60
    POSITIVE LOGITS
     preference
    1.49
     protoimpl
    0.87
    migrationBuilder
    0.79
    preference
    0.77
    UnsafeEnabled
    0.73
     оригіналу
    0.69
    modelBuilder
    0.68
     emphasis
    0.67
     priority
    0.66
     Preference
    0.65
    Activations Density 0.001%

    No Known Activations