© 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. 4300
    Prev
    Next
    INDEX
    Explanations

    comes

    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
     CreateTagHelper
    -0.77
    पया
    -0.65
     NSCoder
    -0.63
    BagLayout
    -0.63
     محفوظة
    -0.62
     mergeFrom
    -0.62
    InitStruct
    -0.60
    ValueStyle
    -0.59
     onBind
    -0.58
    DockStyle
    -0.58
    POSITIVE LOGITS
    oredCriteria
    0.55
    
    0.54
    #
    0.54
     gambe
    0.49
    TEMPO
    0.46
     allmän
    0.46
     länder
    0.45
    letka
    0.45
     économ
    0.44
     participation
    0.43
    Activations Density 0.007%

    No Known Activations