© 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. 2157
    Prev
    Next
    INDEX
    Explanations

    the code string "TP"

    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
    ✭✭
    -0.73
     Ratu
    -0.71
     Arlene
    -0.69
     Yag
    -0.68
     Antrim
    -0.66
    Gale
    -0.66
    franch
    -0.66
     Minang
    -0.65
    ieteur
    -0.65
     Saffron
    -0.65
    POSITIVE LOGITS
    TP
    2.67
    tp
    2.56
     TP
    2.38
     tp
    2.05
    Tp
    1.63
     Tp
    1.31
    tps
    0.98
     TPP
    0.91
     TPU
    0.73
     TPA
    0.67
    Activations Density 0.005%

    No Known Activations