© 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. 4648
    Prev
    Next
    INDEX
    Explanations

    directions

    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
    riwal
    -0.71
    styleType
    -0.64
    verwijspagina
    -0.62
     Infórmanos
    -0.57
     vectorielle
    -0.56
    出版年
    -0.55
     doInBackground
    -0.51
    SpringRunner
    -0.51
     kasarigan
    -0.50
     SqlConnection
    -0.49
    POSITIVE LOGITS
    abay
    0.57
    mans
    0.56
    clusive
    0.54
    ngths
    0.53
    gen
    0.52
    abar
    0.51
    abro
    0.50
    ÁB
    0.50
    ned
    0.49
    rys
    0.49
    Activations Density 0.001%

    No Known Activations