© 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. 91584
    Prev
    Next
    INDEX
    Explanations

    programming/data analysis

    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
    SourceChecksum
    -0.74
    OfYear
    -0.68
     Zwick
    -0.65
     ब्रेकडाउन
    -0.61
     виправивши
    -0.60
    chiali
    -0.60
     дописавши
    -0.59
    InputTagHelper
    -0.58
    StoryboardSegue
    -0.58
     kasarigan
    -0.57
    POSITIVE LOGITS
     للاسماء
    0.57
    #+#
    0.50
    issau
    0.46
    itha
    0.46
     للمعارف
    0.43
    ism
    0.38
    AED
    0.36
    onnay
    0.36
    graphicx
    0.35
     Spectator
    0.35
    Activations Density 0.004%

    No Known Activations