© 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. 5-CLT-HP
    7. 4510
    Prev
    Next
    INDEX
    Explanations

    your

    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
     CreateTagHelper
    -0.53
    於
    -0.46
     surla
    -0.45
    twimg
    -0.45
     and
    -0.43
    lingo
    -0.43
     inasmuch
    -0.42
    Various
    -0.42
    ⓧ
    -0.42
     beyond
    -0.41
    POSITIVE LOGITS
    richTextPanel
    0.81
     Roskov
    0.72
     Wikimedijinoj
    0.70
     invece
    0.65
     grecque
    0.64
    EndContext
    0.60
    Välislingid
    0.59
    GraphicsUnit
    0.58
     hábito
    0.57
     stället
    0.56
    Activations Density 0.005%

    No Known Activations