© 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. 5252
    Prev
    Next
    INDEX
    Explanations

    Research studies

    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
    Попис
    -0.57
    `;
    -0.47
    =?";
    -0.46
     Zulu
    -0.45
    ),),
    -0.44
     becauſe
    -0.44
     Lauter
    -0.44
    :");
    -0.43
    LVANIA
    -0.43
    cephala
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.80
    uxxxx
    0.56
    chen
    0.56
    bej
    0.54
     MonoBehaviour
    0.52
    chov
    0.52
    hydrogenase
    0.50
    juna
    0.49
    mayer
    0.49
    bten
    0.48
    Activations Density 0.002%

    No Known Activations