© 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. 3-RES-MATRYOSHKA-DC
    7. 2687
    Prev
    Next
    INDEX
    Explanations

    the word "trap/rap" and words immediately following it

    oai_token-act-pair · gemini-2.0-flash
    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
    httphttps
    -0.78
    SerializedSize
    -0.77
    tanleria
    -0.75
     Torque
    -0.72
    ValueStyle
    -0.70
    közi
    -0.69
    requestCode
    -0.68
     meningitis
    -0.68
     Stripes
    -0.68
    isler
    -0.68
    POSITIVE LOGITS
     trap
    3.09
     traps
    2.91
    trap
    2.75
     Trap
    2.72
     Traps
    2.50
    Trap
    2.48
     trapping
    2.38
     TRAP
    2.06
     trapped
    1.95
    TRAP
    1.69
    Activations Density 0.003%

    No Known Activations