© 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. 5-CLT-HP
    7. 93601
    Prev
    Next
    INDEX
    Explanations

    denials and statements

    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
    enumi
    -0.68
    AccessorTable
    -0.68
    uxxxx
    -0.62
    wpi
    -0.60
    CloseOperation
    -0.59
    StoryboardSegue
    -0.59
    ThroughAttribute
    -0.57
    verwijspagina
    -0.56
    TagHelper
    -0.54
    setVerticalGroup
    -0.54
    POSITIVE LOGITS
    caj
    0.56
     oublié
    0.52
     doigt
    0.51
     résister
    0.48
     contenir
    0.48
     oleh
    0.48
     inför
    0.48
    IVEREF
    0.48
     ModelExpression
    0.47
     by
    0.46
    Activations Density 0.001%

    No Known Activations