© 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. 20-CLT-HP
    7. 76913
    Prev
    Next
    INDEX
    Explanations

    code/legal/medical documents

    np_max-act-logits · 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
     rằng
    -0.51
     Wikimedijinoj
    -0.48
    atown
    -0.46
    ToBounds
    -0.46
    antwoorde
    -0.45
    TagHelper
    -0.44
    󠁮
    -0.42
    ค์
    -0.42
     october
    -0.41
     gedaan
    -0.41
    POSITIVE LOGITS
    ,
    1.44
     of
    1.26
    Искәрмәләр
    0.70
    AddTagHelper
    0.65
    antMatchers
    0.54
    ̍t
    0.52
     pageContext
    0.52
    teries
    0.52
     consultato
    0.51
     ExecuteAsync
    0.51
    Activations Density 0.000%

    No Known Activations