© 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. 5521
    Prev
    Next
    INDEX
    Explanations

    could not determine pattern. using

    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
    IGraphics
    -0.49
    oids
    -0.47
    bitField
    -0.45
    쁜
    -0.45
    octanol
    -0.45
    niques
    -0.43
    writeFieldEnd
    -0.43
    rscheinlich
    -0.43
    TagNumber
    -0.43
    ógicas
    -0.42
    POSITIVE LOGITS
     purpoſe
    0.57
     Consultez
    0.57
    AnchorTagHelper
    0.54
     Téléchargez
    0.53
     مشين
    0.53
    setVerticalGroup
    0.52
    WebServlet
    0.52
     preſent
    0.51
    lho
    0.50
    ScopeManager
    0.50
    Activations Density 0.000%

    No Known Activations