© 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. 4565
    Prev
    Next
    INDEX
    Explanations

    do

    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
    say
    -0.62
     say
    -0.60
     consider
    -0.51
     fortæ
    -0.48
     piensan
    -0.48
    قول
    -0.48
     consideran
    -0.47
    íslu
    -0.47
    LayoutStyle
    -0.47
     createContext
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.86
    +#+#
    0.76
    ंदीखरीदारी
    0.65
    BeginContext
    0.64
    GetKeyDown
    0.59
     rhestr
    0.56
     betweenstory
    0.55
    EDEFAULT
    0.54
     >=",
    0.54
    SourceChecksum
    0.52
    Activations Density 0.005%

    No Known Activations