© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5740
    Prev
    Next
    INDEX
    Explanations

    most

    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
    !("{
    -0.74
    ItemBackground
    -0.74
     useStyles
    -0.69
    endregion
    -0.67
     otomatig
    -0.63
     Autorizaciones
    -0.62
    قایناق‌لار
    -0.62
    этому
    -0.62
     OFDb
    -0.62
    BufferException
    -0.61
    POSITIVE LOGITS
     mentioned
    0.52
     quoted
    0.50
     notable
    0.49
    TagMode
    0.48
     noted
    0.45
     noticeable
    0.45
     reported
    0.45
    ånd
    0.43
     represented
    0.43
    ometal
    0.43
    Activations Density 0.002%

    No Known Activations