© 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. 4-CLT-HP
    7. 53
    Prev
    Next
    INDEX
    Explanations

    computers and games

    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
    elemField
    -0.57
    huma
    -0.52
     doPost
    -0.51
    chyma
    -0.51
     useStyles
    -0.48
    etna
    -0.47
     nghiệp
    -0.46
     Physically
    -0.45
    WriteTagHelper
    -0.45
    XmlAccessorType
    -0.45
    POSITIVE LOGITS
    <bos>
    0.68
    apimachinery
    0.56
     utafitiHapana
    0.49
    XmlAccessType
    0.47
    клопе
    0.47
    '
    0.47
    exitRule
    0.46
     Amiga
    0.45
    AndroidJUnit
    0.45
    vician
    0.45
    Activations Density 0.068%

    No Known Activations