© 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. 3494
    Prev
    Next
    INDEX
    Explanations

    possessive words

    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
    <bos>
    -0.94
    tanleria
    -0.73
     autorytatywna
    -0.65
    )"),
    -0.59
    ')],
    -0.56
    олові
    -0.54
     Zet
    -0.50
    ometal
    -0.50
    "]();
    -0.49
    }");
    -0.49
    POSITIVE LOGITS
     AssemblyCompany
    0.66
    OGND
    0.65
     محفوظة
    0.64
    __(/*!
    0.57
    +#+#
    0.57
    aarrggbb
    0.57
    //
    0.56
     تضيفلها
    0.55
     оригіналу
    0.53
    MessageTagHelper
    0.52
    Activations Density 2.840%

    No Known Activations