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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10246
    Prev
    Next
    INDEX
    Explanations

    It

    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
    hdessä
    -0.56
    Sprintf
    -0.55
    qvarna
    -0.54
     DataTypes
    -0.54
    rouvez
    -0.53
    ️
    -0.53
    =$?
    -0.52
    ,'\
    -0.52
    mannian
    -0.52
    apeake
    -0.52
    POSITIVE LOGITS
    MigrationBuilder
    0.68
    NameInMap
    0.61
    LookAnd
    0.52
    Diweddarwch
    0.52
     فريبيس
    0.51
     يتيمه
    0.50
     utafitiHapana
    0.50
    WebVitals
    0.49
    IUrlHelper
    0.49
     yetu
    0.48
    Activations Density 0.012%

    No Known Activations