© 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. 15431
    Prev
    Next
    INDEX
    Explanations

    toughness

    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
    ifer
    -1.00
    IFER
    -0.87
     تانيه
    -0.51
    GenerationType
    -0.50
    rile
    -0.48
    gan
    -0.45
     trabal
    -0.44
    birds
    -0.44
    ifers
    -0.43
    fie
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.77
     CreateTagHelper
    0.63
    ILayout
    0.62
     Wicidata
    0.62
     pourtant
    0.60
    NodeInfo
    0.60
     Holders
    0.59
     montr
    0.58
     Quo
    0.58
     Baruch
    0.57
    Activations Density 0.250%

    No Known Activations