© 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. 5-CLT-HP
    7. 92347
    Prev
    Next
    INDEX
    Explanations

    rankings, offers, comparisons

    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
    anhas
    -0.54
    delà
    -0.50
    YSTEM
    -0.50
    semantics
    -0.49
    wider
    -0.48
    énd
    -0.48
     OnClickListener
    -0.48
    ArgumentParser
    -0.48
    eroll
    -0.47
     kepada
    -0.47
    POSITIVE LOGITS
     tartalomajánló
    0.61
     nakalista
    0.61
     الرياضيه
    0.60
    AndroidJUnit
    0.54
    encodeWith
    0.52
    ✨:
    0.52
    +#+
    0.52
    Aholisi
    0.51
     Empieza
    0.50
    owohl
    0.50
    Activations Density 0.014%

    No Known Activations