© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43994
    Prev
    Next
    INDEX
    Explanations

    was

    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
    GEBURTSDATUM
    -0.88
    oredCriteria
    -0.79
    tagHelperRunner
    -0.66
    twas
    -0.64
     otomatig
    -0.60
    SourceChecksum
    -0.59
     betweenstory
    -0.56
    protoimpl
    -0.56
     AspNetCore
    -0.55
    Cyfeiriadau
    -0.55
    POSITIVE LOGITS
     now
    0.64
     is
    0.56
     rootReducer
    0.56
    igshid
    0.56
    Sekarang
    0.56
     FontWeight
    0.54
     Chwiliwch
    0.54
     maintenant
    0.53
    WriteBarrier
    0.53
    ษ
    0.52
    Activations Density 0.215%

    No Known Activations