© 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. 1-CLT-HP
    4. 45544
    Prev
    Next
    INDEX
    Explanations

    to

    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
    BeginContext
    -0.67
     تضيفلها
    -0.63
     beginnings
    -0.63
    esModule
    -0.62
     søndag
    -0.61
    withIdentifier
    -0.60
    OGND
    -0.60
    shall
    -0.59
     funerals
    -0.59
     Nicolai
    -0.59
    POSITIVE LOGITS
     use
    0.68
    <bos>
    0.63
     initComponents
    0.61
    use
    0.61
     just
    0.57
     />\
    0.55
    ]")]
    0.54
    MessageTagHelper
    0.53
    HtmlAttribute
    0.49
     ask
    0.48
    Activations Density 0.009%

    No Known Activations