© 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-CLT-HP
    7. 42494
    Prev
    Next
    INDEX
    Explanations

    or

    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
     onPage
    -0.58
     GD
    -0.57
    Derp
    -0.54
    MessageTagHelper
    -0.53
    Източници
    -0.52
    ]")]
    -0.52
     ویکی‌پدیا
    -0.52
    addGap
    -0.50
    mism
    -0.49
    avras
    -0.49
    POSITIVE LOGITS
    ConstraintMaker
    0.66
    ########.
    0.61
     szint
    0.59
     espirituales
    0.54
     Binder
    0.50
    actionMode
    0.49
     batterie
    0.49
    InjectAttribute
    0.48
     always
    0.48
     cantidades
    0.47
    Activations Density 0.068%

    No Known Activations