© 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. 4-CLT-HP
    7. 2932
    Prev
    Next
    INDEX
    Explanations

    been

    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
    Referències
    -0.48
     électroniques
    -0.47
    ikut
    -0.47
    }\]
    -0.47
     feltro
    -0.47
     quarries
    -0.47
    Excerpts
    -0.46
     automatiques
    -0.46
     dimentic
    -0.46
    }^\
    -0.46
    POSITIVE LOGITS
    webElementXpaths
    0.74
     a
    0.73
     AssemblyCulture
    0.69
     HasFactory
    0.65
     defaultstate
    0.64
     identified
    0.63
     CreateTagHelper
    0.63
     another
    0.63
    Personendaten
    0.62
    ಞ
    0.60
    Activations Density 0.006%

    No Known Activations