© 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. 0-CLT-HP
    7. 43504
    Prev
    Next
    INDEX
    Explanations

    oste

    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
    icha
    -0.75
    cas
    -0.67
     cas
    -0.64
     Cassel
    -0.57
    oste
    -0.54
    ald
    -0.54
     Curry
    -0.54
    issa
    -0.53
     Η
    -0.51
     autorytatywna
    -0.51
    POSITIVE LOGITS
    ^(@)
    0.91
     Monfieur
    0.88
     myſelf
    0.87
     Majefty
    0.84
     pleaſure
    0.84
     ―――――
    0.83
     themſelves
    0.83
     GenerationType
    0.78
     Efq
    0.78
     houſe
    0.77
    Activations Density 1.719%

    No Known Activations