© 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. 0-CLT-HP
    7. 97765
    Prev
    Next
    INDEX
    Explanations

    workplace

    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
     Rocks
    -1.18
     rocks
    -1.02
     ROCKS
    -0.98
    rocks
    -0.97
    Rocks
    -0.97
     autorytatywna
    -0.79
    AddTagHelper
    -0.69
    Autoritní
    -0.68
    ///</
    -0.66
    Composable
    -0.65
    POSITIVE LOGITS
    styleUrls
    0.57
    man
    0.57
    ake
    0.55
    ur
    0.48
    gan
    0.48
    om
    0.47
    ak
    0.46
    cor
    0.46
    lem
    0.46
    n
    0.45
    Activations Density 0.350%

    No Known Activations