© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94328
    Prev
    Next
    INDEX
    Explanations

    in

    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
    __*/
    -0.99
    verwijspagina
    -0.97
    Personendaten
    -0.87
    IntoConstraints
    -0.81
     propOrder
    -0.80
     tuesday
    -0.79
     Tuesday
    -0.79
     wednesday
    -0.75
     Wednesday
    -0.75
     thursday
    -0.74
    POSITIVE LOGITS
     a
    0.55
     an
    0.48
    kijken
    0.46
     kolei
    0.42
    ọa
    0.40
     association
    0.38
    zetten
    0.37
     року
    0.36
    abri
    0.36
     alapján
    0.35
    Activations Density 0.001%

    No Known Activations