© 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. 72352
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
    unnitel
    -0.60
    windowFixed
    -0.58
     AssemblyCulture
    -0.58
    igshid
    -0.55
     Wain
    -0.54
     dài
    -0.53
    mada
    -0.52
     pinulongan
    -0.52
    dited
    -0.51
    mated
    -0.51
    POSITIVE LOGITS
    цездатний
    0.52
     Parcelable
    0.47
    хьтан
    0.47
    nonatomic
    0.47
    SpringBootTest
    0.47
     архивлан
    0.45
     HttpHeaders
    0.44
     GenerationType
    0.44
    hibitions
    0.44
     noDo
    0.44
    Activations Density 0.000%

    No Known Activations