© 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. 3159
    Prev
    Next
    INDEX
    Explanations

    code, imports and programming

    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
     arşivlendi
    -0.61
     Winaray
    -0.59
    WriteBarrier
    -0.59
     disambiguazione
    -0.59
    AsUp
    -0.58
     BrowserRouter
    -0.57
    AutoScaleMode
    -0.56
    DrawerToggle
    -0.56
     iprot
    -0.55
     EconPapers
    -0.55
    POSITIVE LOGITS
     the
    0.65
    ziała
    0.44
     svět
    0.43
     THE
    0.43
    seed
    0.43
     Parkway
    0.43
    ข
    0.42
     minas
    0.41
    falen
    0.41
    mannen
    0.41
    Activations Density 0.002%

    No Known Activations