© 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. 4128
    Prev
    Next
    INDEX
    Explanations

    segments of text containing explicit references to sexual activity or explicit sexual language

    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
    migrationBuilder
    -0.72
    ViewInit
    -0.60
    ITAR
    -0.57
    mallows
    -0.56
    THON
    -0.55
    "]();
    -0.54
    стру
    -0.53
    AlertDialog
    -0.52
    ashian
    -0.52
    وبات
    -0.52
    POSITIVE LOGITS
     motion
    2.48
    motion
    2.31
     Motion
    2.30
    Motion
    2.19
     MOTION
    2.11
     motions
    1.83
     Motions
    1.75
    motions
    1.59
    MOTION
    1.48
     Bewegung
    1.03
    Activations Density 0.010%

    No Known Activations