© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2785
    Prev
    Next
    INDEX
    Explanations

    direction, focus

    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
     فريبيس
    -0.71
     Photocase
    -0.70
    Personendaten
    -0.66
    تقاوى
    -0.66
     resourceCulture
    -0.65
    ⓧ
    -0.65
     gradova
    -0.63
     ostavi
    -0.63
     betweenstory
    -0.60
     <>",
    -0.55
    POSITIVE LOGITS
     improving
    0.68
     enhancing
    0.67
     boosting
    0.66
     solving
    0.62
     increasing
    0.62
     combating
    0.61
     fostering
    0.59
     strengthening
    0.58
     getting
    0.57
     easing
    0.57
    Activations Density 0.002%

    No Known Activations