© 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. 10486
    Prev
    Next
    INDEX
    Explanations

    body parts

    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
    DidLoad
    -0.56
     pavillon
    -0.54
     forks
    -0.51
    tix
    -0.47
     Forks
    -0.46
     comigo
    -0.46
    crollView
    -0.46
     veneta
    -0.46
     halls
    -0.46
    hoes
    -0.45
    POSITIVE LOGITS
    LabelTagHelper
    0.65
    DeleteBehavior
    0.61
    EndGlobalSection
    0.59
    AndEndTag
    0.56
     Walkover
    0.56
     Roskov
    0.54
    TemporalType
    0.54
    URLException
    0.52
    inghouse
    0.51
    TintMode
    0.50
    Activations Density 0.077%

    No Known Activations