© 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. 4887
    Prev
    Next
    INDEX
    Explanations

    little bit

    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
     pleaſure
    -0.67
     незавершена
    -0.66
    ніципа
    -0.63
     WaitForSeconds
    -0.63
     Italijanski
    -0.62
     affair
    -0.62
     Theſe
    -0.61
    SourceChecksum
    -0.61
     nô
    -0.60
    XmlAccessorType
    -0.60
    POSITIVE LOGITS
     about
    0.93
     About
    0.89
    About
    0.75
    rawDesc
    0.67
     ABOUT
    0.64
     off
    0.58
    about
    0.58
     о
    0.55
     like
    0.55
     o
    0.53
    Activations Density 0.001%

    No Known Activations