© 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. 97316
    Prev
    Next
    INDEX
    Explanations

    So

    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
     So
    -1.42
     And
    -1.20
    So
    -0.97
     But
    -0.87
     and
    -0.82
     so
    -0.79
    And
    -0.74
     Or
    -0.73
     AND
    -0.73
     or
    -0.66
    POSITIVE LOGITS
     myſelf
    1.10
     Monfieur
    1.01
     Majefty
    1.00
     Theſe
    0.98
     ſeveral
    0.95
     avoient
    0.93
     Diſ
    0.93
     purpoſe
    0.93
    ſelf
    0.92
     uſ
    0.91
    Activations Density 1.051%

    No Known Activations