© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41136
    Prev
    Next
    INDEX
    Explanations

    ylon

    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
    ylon
    -1.41
    YLON
    -0.78
     cre
    -0.63
     Horner
    -0.52
    INTRODUCCIÓN
    -0.45
    eradish
    -0.44
     fer
    -0.42
    Introdução
    -0.41
    ത
    -0.41
     Thore
    -0.40
    POSITIVE LOGITS
    LabelTagHelper
    0.70
    RenderAtEndOf
    0.70
     Bioaccumulative
    0.60
    WithIOException
    0.59
    WriteAttribute
    0.58
    DECREF
    0.57
     dė
    0.57
    arakhand
    0.57
     mérit
    0.57
     linkovi
    0.56
    Activations Density 1.624%

    No Known Activations