© 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. 12190
    Prev
    Next
    INDEX
    Explanations

    references to a young boy or lad

    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
    DockStyle
    -0.69
     Administrativna
    -0.69
    tanleria
    -0.68
    nagel
    -0.66
    UnitTesting
    -0.65
    ométrique
    -0.63
    SerializedName
    -0.61
    UnusedPrivate
    -0.60
     мәкал
    -0.58
    enis
    -0.57
    POSITIVE LOGITS
     lad
    3.45
    lad
    2.58
     Lad
    2.47
    Lad
    2.38
     LAD
    1.75
    LAD
    1.75
     lads
    1.45
    lads
    1.45
     ladd
    1.24
     ladle
    1.11
    Activations Density 0.002%

    No Known Activations