© 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. 5-CLT-HP
    7. 4526
    Prev
    Next
    INDEX
    Explanations

    children

    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
     >=",
    -0.57
     Wiktionnaire
    -0.55
    édez
    -0.55
    rungsseite
    -0.53
     يتيمه
    -0.51
     Drapeau
    -0.51
     فہرست
    -0.51
    Extinguishing
    -0.50
    FURTHER
    -0.47
    ENTOS
    -0.46
    POSITIVE LOGITS
     attends
    0.57
     JpaRepository
    0.56
    onViewCreated
    0.56
    .*")]
    0.55
    slidesToShow
    0.55
    ]--;
    0.54
     StatefulWidget
    0.53
    xaml
    0.52
    Бахар
    0.52
    featureID
    0.52
    Activations Density 0.001%

    No Known Activations