© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 5017
    Prev
    Next
    INDEX
    Explanations

    Salvation

    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
    ViewById
    -0.54
     Dostupné
    -0.53
    card
    -0.51
    NOST
    -0.50
    getInputStream
    -0.50
    ditionally
    -0.50
    getDescriptor
    -0.49
     initComponents
    -0.49
     Nishi
    -0.49
    adaptiveStyles
    -0.49
    POSITIVE LOGITS
    IUrlHelper
    0.61
     ProtoMessage
    0.54
     MainAxisSize
    0.52
     betweenstory
    0.51
     SqlCommand
    0.46
    مراجع
    0.46
    WithIOException
    0.44
    SHADER
    0.44
    scriptcase
    0.44
    로그
    0.43
    Activations Density 0.024%

    No Known Activations