© 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. 20-CLT-HP
    7. 77844
    Prev
    Next
    INDEX
    Explanations

    technical/formal documentation

    np_max-act-logits · 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
    ParallelGroup
    -0.65
    GEBURTSDATUM
    -0.64
    SequentialGroup
    -0.59
     يتيمه
    -0.57
    tagHelperRunner
    -0.57
    RegistryLite
    -0.55
    Tikang
    -0.52
     esternos
    -0.52
    argout
    -0.52
    opy
    -0.51
    POSITIVE LOGITS
    onViewCreated
    0.59
    nsf
    0.51
     filles
    0.49
    listdir
    0.49
    Im
    0.47
     rempla
    0.47
     höchst
    0.46
     Ush
    0.46
    elar
    0.46
     sabato
    0.45
    Activations Density 0.005%

    No Known Activations