Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 149
    Prev
    Next
    INDEX
    Explanations

    the

    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
     незавершена
    -0.71
    HtmlAttribute
    -0.69
    فایل‌لار
    -0.65
    nonatomic
    -0.55
    DebuggerNonUser
    -0.55
    ynı
    -0.54
    SBATCH
    -0.54
     StatelessWidget
    -0.52
     تضيفلها
    -0.52
    Бахар
    -0.52
    POSITIVE LOGITS
    ništ
    0.48
     animal
    0.48
    usei
    0.47
    Affirmed
    0.46
     perfil
    0.45
    pagation
    0.44
     administration
    0.44
     ICF
    0.43
    hef
    0.43
    Serves
    0.43
    Activations Density 0.031%

    No Known Activations