© 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. 5804
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    AccessorTable
    -0.54
    psack
    -0.45
     demande
    -0.44
     parts
    -0.44
     pega
    -0.44
    jspx
    -0.43
    명
    -0.42
     cred
    -0.42
    ίσ
    -0.41
    demand
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    0.78
    rungsseite
    0.66
    Datuak
    0.66
     Loos
    0.63
    GraphicsUnit
    0.60
    waitKey
    0.59
     مواليد
    0.58
     MainAxisSize
    0.57
    RTEX
    0.57
    uality
    0.57
    Activations Density 0.005%

    No Known Activations