© 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. 3822
    Prev
    Next
    INDEX
    Explanations

    dates

    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
     CreateTagHelper
    -0.64
    lgari
    -0.63
     umbilical
    -0.60
     AssemblyTitle
    -0.59
     Nove
    -0.59
     umbi
    -0.59
    NUMX
    -0.59
     Parad
    -0.57
     Karol
    -0.57
    Демографія
    -0.57
    POSITIVE LOGITS
     élas
    0.53
     quantités
    0.51
     renseignements
    0.51
     avoient
    0.50
     racines
    0.50
     identité
    0.50
     étoit
    0.50
     pierres
    0.48
     afectan
    0.47
     potuto
    0.47
    Activations Density 0.012%

    No Known Activations