© 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. 0-CLT-HP
    7. 43603
    Prev
    Next
    INDEX
    Explanations

    banks or code

    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
    bank
    -1.23
    BANK
    -0.67
    arden
    -0.64
    Bank
    -0.55
    banken
    -0.49
    idal
    -0.49
    lieu
    -0.46
     bank
    -0.46
    msgTypes
    -0.46
    isk
    -0.46
    POSITIVE LOGITS
    expandindo
    0.91
    InitVars
    0.87
    er
    0.81
    BrowserModule
    0.80
    afficheront
    0.78
    IndentedString
    0.78
     Paglinawan
    0.76
    ers
    0.74
     defaultstate
    0.74
    ftagPool
    0.73
    Activations Density 0.191%

    No Known Activations