© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3992
    Prev
    Next
    INDEX
    Explanations

    shown

    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
    èdia
    -0.56
     tartalomajánló
    -0.54
     gawas
    -0.53
     lèvres
    -0.52
     costuma
    -0.50
     הכי
    -0.46
     genoux
    -0.46
     bébés
    -0.44
     prêts
    -0.44
    IntoConstraints
    -0.43
    POSITIVE LOGITS
     mergeFrom
    0.60
     numerous
    0.57
     multiple
    0.57
    Numerous
    0.54
     onCancelled
    0.53
    InvalidProtocol
    0.52
    Rhestr
    0.52
    jsxFileName
    0.52
     CreateTagHelper
    0.51
    NewUrlParser
    0.50
    Activations Density 0.002%

    No Known Activations