© 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. 62
    Prev
    Next
    INDEX
    Explanations

    as

    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
    instancetype
    -0.53
     nó
    -0.49
     consultato
    -0.49
    stanti
    -0.48
    gameserver
    -0.47
    IBAction
    -0.46
     nonatomic
    -0.46
    WebServlet
    -0.45
     rubbish
    -0.45
     trang
    -0.44
    POSITIVE LOGITS
     Signalez
    0.70
    ArgumentParser
    0.68
     كومونز
    0.65
    Autoritní
    0.63
    ंदीखरीदारी
    0.59
     kasarigan
    0.58
    UrlResolution
    0.57
    RenderAtEndOf
    0.57
     >=",
    0.56
    ftagPool
    0.56
    Activations Density 0.003%

    No Known Activations