© 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. 40328
    Prev
    Next
    INDEX
    Explanations

    loved

    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
     for
    -0.66
     to
    -0.59
     in
    -0.56
     kív
    -0.55
    '
    -0.51
     beroperasi
    -0.51
     as
    -0.50
    ؤال
    -0.49
     antaranya
    -0.48
     I
    -0.48
    POSITIVE LOGITS
     Efq
    0.81
     ―――――
    0.77
     ſever
    0.76
     ſmall
    0.76
     Houſe
    0.76
     Reſ
    0.75
    parsedMessage
    0.75
     myſelf
    0.75
     ſtate
    0.74
     Majefty
    0.73
    Activations Density 0.036%

    No Known Activations