© 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. 77701
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    +#+#
    -0.64
     تضيفلها
    -0.63
    :"-"`
    -0.62
    ysty
    -0.51
    mergeFrom
    -0.50
    Sklici
    -0.50
     发表于
    -0.49
    endorff
    -0.48
    เภ
    -0.47
     AssemblyProduct
    -0.45
    POSITIVE LOGITS
     doInBackground
    0.70
     disambiguazione
    0.66
     ActionResult
    0.58
    casi
    0.55
    ╦
    0.51
     MNRAS
    0.51
     tartalomajánló
    0.50
    cipar
    0.50
    StreetMap
    0.49
    AddTagHelper
    0.48
    Activations Density 0.000%

    No Known Activations