© 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. 1-CLT-HP
    7. 15176
    Prev
    Next
    INDEX
    Explanations

    transfer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfer
    -1.34
    transfer
    -1.27
     Transfer
    -1.14
     transferring
    -1.11
     transferred
    -1.08
    Transfer
    -1.07
     transfers
    -1.06
     transferência
    -1.04
     TRANSFER
    -1.02
     transferencia
    -0.97
    POSITIVE LOGITS
     ویکی‌پدی
    0.83
    tagext
    0.65
    ed
    0.61
    featureID
    0.59
    rate
    0.58
    RegistryLite
    0.57
    GroupLayout
    0.57
    RenderAtEndOf
    0.57
    spesies
    0.56
    ential
    0.54
    Activations Density 0.015%

    No Known Activations