© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41235
    Prev
    Next
    INDEX
    Explanations

    research and artistic explorations

    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
     Movements
    -0.81
    клопе
    -0.71
    movements
    -0.69
     movements
    -0.69
    OGND
    -0.68
     autorytatywna
    -0.68
     вікі
    -0.63
     незавершена
    -0.62
    లాలు
    -0.61
     Roskov
    -0.60
    POSITIVE LOGITS
     peasants
    0.55
    Slf
    0.50
    Capítulo
    0.50
     praktis
    0.49
    cloudfront
    0.48
    gcf
    0.47
    setContentView
    0.45
     BaseActivity
    0.44
    FailureListener
    0.44
    ⓘ
    0.44
    Activations Density 1.537%

    No Known Activations