© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2248
    Prev
    Next
    INDEX
    Explanations

    computing, science

    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
    Dữ
    -0.56
     তারিখ
    -0.54
    }());
    -0.52
    brokes
    -0.50
     surfactant
    -0.50
    viedo
    -0.49
    ophor
    -0.49
    winston
    -0.48
    protoc
    -0.48
    estal
    -0.48
    POSITIVE LOGITS
    ReusableCell
    0.69
    Composable
    0.52
     viñ
    0.47
    󠁴
    0.47
    Entry
    0.46
    CloseOperation
    0.45
    devamını
    0.45
     Bagh
    0.45
    ország
    0.45
    ۰۰
    0.45
    Activations Density 0.003%

    No Known Activations