© 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. 0-CLT-HP
    4. 2032
    Prev
    Next
    INDEX
    Explanations

    ers

    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
    ers
    -1.95
    ERS
    -1.28
    er
    -0.93
    ER
    -0.82
    ersk
    -0.76
    ists
    -0.72
    ingly
    -0.67
    erski
    -0.66
    sters
    -0.65
     itſelf
    -0.64
    POSITIVE LOGITS
    djangoproject
    0.67
    DeleteBehavior
    0.56
    ensitive
    0.56
    migrationBuilder
    0.53
    <bos>
    0.52
    فحه
    0.50
    ValueGeneration
    0.49
    }();
    0.46
    QMetaType
    0.46
    TagHelpers
    0.46
    Activations Density 0.014%

    No Known Activations