© 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. 4343
    Prev
    Next
    INDEX
    Explanations

    space

    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
    enumi
    -0.63
    adaptiveStyles
    -0.61
     OkHttpClient
    -0.58
    __(/*!
    -0.58
    
    -0.56
    γον
    -0.55
    EDEFAULT
    -0.54
    %"),
    -0.53
    彿
    -0.52
    %</
    -0.51
    POSITIVE LOGITS
    tagHelperRunner
    0.81
    EndContext
    0.69
    InstrumentedTest
    0.57
     vermelhas
    0.57
     générations
    0.55
    aarrggbb
    0.54
     brancas
    0.54
     rangs
    0.53
     comerciais
    0.52
     pacchetto
    0.50
    Activations Density 0.001%

    No Known Activations