© 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. 5-CLT-HP
    7. 96264
    Prev
    Next
    INDEX
    Explanations

    diversity or difference

    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
    AddTagHelper
    -0.62
    UrlResolution
    -0.56
    AutoScale
    -0.53
    ImageContext
    -0.52
    ⓧ
    -0.51
    fillType
    -0.51
     nakalista
    -0.49
     समीक्षक
    -0.47
    참고
    -0.47
     NUKAT
    -0.46
    POSITIVE LOGITS
    WireFormatLite
    0.60
    tamment
    0.58
    WaitGroup
    0.58
     femei
    0.57
     morire
    0.57
     strconv
    0.56
     PyLong
    0.56
     marquées
    0.55
     GenerationType
    0.55
    StackNavigator
    0.52
    Activations Density 0.002%

    No Known Activations