© 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. 72810
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    Referanser
    -0.44
     setOpen
    -0.41
     hereditary
    -0.41
     alarm
    -0.40
    VersionUID
    -0.39
    metheus
    -0.39
     conce
    -0.38
    routeProvider
    -0.37
     mec
    -0.37
    Kritik
    -0.37
    POSITIVE LOGITS
     referenties
    0.64
     Donde
    0.63
     Wanted
    0.63
    zungs
    0.63
    inafter
    0.62
    onomía
    0.61
    LookAnd
    0.60
     Paglinawan
    0.59
    InjectAttribute
    0.58
     Freed
    0.58
    Activations Density 0.002%

    No Known Activations