© 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. 5079
    Prev
    Next
    INDEX
    Explanations

    of

    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
     MainAxisSize
    -0.87
    Personendaten
    -0.85
    ArrowToggle
    -0.80
     <=",
    -0.79
    Архівовано
    -0.77
    parsedMessage
    -0.75
    Tikang
    -0.74
    endphp
    -0.72
    NUMX
    -0.71
    ArgsConstructor
    -0.69
    POSITIVE LOGITS
     homes
    0.39
     communities
    0.38
     dimiliki
    0.37
    garek
    0.36
     a
    0.36
    Ծանոթ
    0.36
     warga
    0.36
    térature
    0.35
    empuan
    0.35
     iemand
    0.35
    Activations Density 0.003%

    No Known Activations