© 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. 20-CLT-HP
    7. 73617
    Prev
    Next
    INDEX
    Explanations

    Code or foreign languages

    np_max-act-logits · 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
    RetentionPolicy
    -0.62
     EconPapers
    -0.54
     CreateTagHelper
    -0.54
    HttpFoundation
    -0.52
    原始内容存档于
    -0.50
    riwal
    -0.49
    ndice
    -0.48
    RenderAtEndOf
    -0.47
    ineno
    -0.47
     anhyd
    -0.47
    POSITIVE LOGITS
    dasarkan
    0.55
    rachtet
    0.54
     ::=
    0.54
    horabuena
    0.53
    ()]);
    0.51
     Diretto
    0.50
     خارجية
    0.49
     élas
    0.49
     abstrato
    0.47
     RIPRODUZIONE
    0.47
    Activations Density 0.000%

    No Known Activations