© 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. 2681
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Galli
    -0.59
     pageContext
    -0.50
    Filmografie
    -0.48
    disposing
    -0.45
    ActionPerformed
    -0.44
    мера
    -0.43
     stopped
    -0.43
    েই
    -0.43
     pitched
    -0.43
    gapi
    -0.42
    POSITIVE LOGITS
    AddTagHelper
    0.60
    מבר
    0.60
     betweenstory
    0.60
     ويكيپيديا
    0.59
    ThroughAttribute
    0.56
     createSlice
    0.56
     ModelExpression
    0.55
     internetowa
    0.55
    Filler
    0.55
     autorytatywna
    0.54
    Activations Density 0.001%

    No Known Activations