© 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. 91534
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
     viewDidLoad
    -0.79
     ligiloj
    -0.75
     فريبيس
    -0.75
    ArrowToggle
    -0.73
    Personensuche
    -0.65
    UserScript
    -0.65
     CreateTagHelper
    -0.65
    IntoConstraints
    -0.63
     ujednoznacz
    -0.63
    InstanceState
    -0.62
    POSITIVE LOGITS
     method
    0.56
    method
    0.47
     version
    0.45
    then
    0.45
     palju
    0.43
     procedure
    0.40
    version
    0.40
     tchèque
    0.40
     biens
    0.40
    all
    0.40
    Activations Density 0.001%

    No Known Activations