© 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. 2694
    Prev
    Next
    INDEX
    Explanations

    survey

    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
     GenerationType
    -0.57
     avoient
    -0.51
     étoient
    -0.48
    хьтан
    -0.45
    einander
    -0.45
    rungsseite
    -0.45
    awakeFromNib
    -0.43
     écoulé
    -0.43
     prêtres
    -0.42
     religieuses
    -0.41
    POSITIVE LOGITS
     pinulongan
    0.69
    Portale
    0.65
     comments
    0.62
     allies
    0.62
    prepareStatement
    0.59
     فريبيس
    0.59
     Ferdinand
    0.57
    @
    0.57
    ---*/
    0.56
    WebVitals
    0.56
    Activations Density 0.000%

    No Known Activations