© 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. 2641
    Prev
    Next
    INDEX
    Explanations

    looking

    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
     utafitiHapana
    -0.59
     purpoſe
    -0.59
    ườ
    -0.58
    voorbeeld
    -0.56
    ,:),
    -0.54
     GenerationType
    -0.54
     podí
    -0.54
     looked
    -0.53
     look
    -0.53
     برانيه
    -0.53
    POSITIVE LOGITS
    برى
    0.49
     pré
    0.49
    нович
    0.49
    Gön
    0.48
    ależy
    0.48
    ίσ
    0.47
    WebControls
    0.47
     vives
    0.47
     préc
    0.46
     Honig
    0.46
    Activations Density 0.023%

    No Known Activations