© 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. 2314
    Prev
    Next
    INDEX
    Explanations

    Code/Data and Drug information

    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
     Mover
    -0.58
     Painter
    -0.55
     OnInit
    -0.52
     ſur
    -0.52
     useStyles
    -0.50
    šanu
    -0.50
     AppDelegate
    -0.50
     Delegate
    -0.50
     Zuid
    -0.50
     Lead
    -0.50
    POSITIVE LOGITS
     محفوظة
    0.64
     <<<<<<<<<<<<<<
    0.61
     الاطلاع
    0.59
     TextInputType
    0.57
    AndEndTag
    0.57
    Hentet
    0.54
    VersionUID
    0.54
     defaultstate
    0.52
    Geplaatst
    0.52
     meeting
    0.50
    Activations Density 0.010%

    No Known Activations