© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92536
    Prev
    Next
    INDEX
    Explanations

    the

    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
     vermelhas
    -0.47
    WriteTagHelper
    -0.47
     pinulongan
    -0.43
     vastaan
    -0.42
    lig
    -0.40
    rungsseite
    -0.40
    Kilder
    -0.38
     beginnetje
    -0.38
    <bos>
    -0.37
     Wiktionnaire
    -0.37
    POSITIVE LOGITS
    EndTag
    0.67
     >=",
    0.66
    StreetMap
    0.64
     fact
    0.62
     kasarigan
    0.61
     EconPapers
    0.60
    UserScript
    0.60
    complexContent
    0.60
    ächs
    0.60
    étisme
    0.60
    Activations Density 0.001%

    No Known Activations