© 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. 11300
    Prev
    Next
    INDEX
    Explanations

    references to the name or role of a specific individual, particularly related to the concept of a "Kid" or young person

    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
     kid
    -1.10
     dude
    -0.64
     createState
    -0.60
    oughby
    -0.57
    redient
    -0.57
     fucker
    -0.55
    loyer
    -0.54
     myn
    -0.54
    fucker
    -0.52
     Timp
    -0.52
    POSITIVE LOGITS
    KID
    1.20
    Kid
    1.13
    kids
    1.11
    kid
    1.05
     Kid
    1.02
    Kids
    0.94
    KIDS
    0.89
     Kids
    0.85
     KID
    0.79
     Kidd
    0.63
    Activations Density 0.001%

    No Known Activations