© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1468
    Prev
    Next
    INDEX
    Explanations

    increasing decreasing

    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
    发表于
    -0.72
     שוליים
    -0.72
    expandindo
    -0.68
     يتيمه
    -0.68
    RenderAtEndOf
    -0.65
     estimés
    -0.65
    --)
    
    -0.63
     esterni
    -0.63
    
    -0.63
    findpost
    -0.61
    POSITIVE LOGITS
     nada
    0.51
     an
    0.48
     gynnwys
    0.45
     overall
    0.45
     the
    0.44
     a
    0.44
     Grossman
    0.44
    érien
    0.44
     men
    0.43
    cep
    0.43
    Activations Density 0.071%

    No Known Activations