© 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. 91829
    Prev
    Next
    INDEX
    Explanations

    master

    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
    KommentareTeilen
    -0.59
    рес
    -0.56
     Specialties
    -0.54
     Affinity
    -0.54
    waitKey
    -0.54
     ferdig
    -0.54
     Serum
    -0.54
     Status
    -0.53
    InsertCommand
    -0.53
    Tikang
    -0.52
    POSITIVE LOGITS
    WebControls
    0.59
    发表于
    0.56
     AssemblyCulture
    0.54
     []:
    0.54
    IVATION
    0.52
    openConnection
    0.50
    setLayoutManager
    0.49
     nonatomic
    0.49
    wpi
    0.48
    nonatomic
    0.47
    Activations Density 0.007%

    No Known Activations