© 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. 2822
    Prev
    Next
    INDEX
    Explanations

    and

    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
    tenham
    -0.51
    Parcelize
    -0.45
     tri
    -0.42
    estra
    -0.40
     dig
    -0.40
     Co
    -0.39
    畢竟
    -0.39
    adrez
    -0.39
    毕竟
    -0.39
     den
    -0.38
    POSITIVE LOGITS
     myſelf
    0.80
    RefNanny
    0.71
     Monfieur
    0.71
     whoſe
    0.71
     indisponible
    0.71
     ModelExpression
    0.69
     uſed
    0.69
    BeginInit
    0.68
     bParam
    0.68
     houſe
    0.68
    Activations Density 0.009%

    No Known Activations