© 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. 0-CLT-HP
    7. 94025
    Prev
    Next
    INDEX
    Explanations

    mentions/discussions of something

    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
    Personendaten
    -0.94
    Personensuche
    -0.94
    InjectAttribute
    -0.92
    ValueGeneration
    -0.89
     الرياضيه
    -0.88
    脚注の使い方
    -0.85
    LookAnd
    -0.85
    AddTagHelper
    -0.84
    CloseOperation
    -0.84
     الحره
    -0.82
    POSITIVE LOGITS
    springframework
    0.55
    -
    0.54
     ilmo
    0.52
    far
    0.52
     
    0.49
     yö
    0.48
     anecdotal
    0.48
    бут
    0.48
    mucha
    0.48
    2
    0.48
    Activations Density 0.014%

    No Known Activations