© 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. 10430
    Prev
    Next
    INDEX
    Explanations

    creation or result

    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
     وتسجيلات
    -0.92
    GEBURTSDATUM
    -0.85
     WaitForSeconds
    -0.64
     Мексичка
    -0.63
    tinyos
    -0.62
    حياته
    -0.62
     beginnetje
    -0.61
    httphttps
    -0.60
    ReusableCell
    -0.59
     createState
    -0.59
    POSITIVE LOGITS
    Попис
    0.49
     poffible
    0.46
    ledem
    0.46
    省市镇
    0.44
    asional
    0.44
    deburg
    0.43
     kasarigan
    0.43
     Roskov
    0.42
     Angleterre
    0.41
     scuro
    0.40
    Activations Density 0.008%

    No Known Activations