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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3443
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    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
    infra
    -0.52
    iser
    -0.50
    vir
    -0.47
    interaction
    -0.45
     مرئيه
    -0.44
    gris
    -0.43
    ISER
    -0.43
     sutil
    -0.43
     interacting
    -0.42
    VISUAL
    -0.42
    POSITIVE LOGITS
     للاسماء
    0.70
    GOTREF
    0.65
    AddTagHelper
    0.65
    WriteTagHelper
    0.63
     HttpNotFound
    0.61
    Atsauces
    0.59
    GHIJKLM
    0.59
    writeField
    0.59
     الرياضيه
    0.58
     Mawr
    0.57
    Activations Density 0.001%

    No Known Activations