© 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. 71986
    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
    NameInMap
    -0.74
    thâu
    -0.73
    期刊论文
    -0.72
    UnsafeEnabled
    -0.68
    Ծանոթ
    -0.68
    хьтан
    -0.66
    OGND
    -0.61
     fevere
    -0.61
     Signalez
    -0.61
    ResponseWriter
    -0.60
    POSITIVE LOGITS
     säll
    0.51
     âgé
    0.41
    łuż
    0.40
    supervisor
    0.40
     griego
    0.40
     hemma
    0.39
    las
    0.39
     samarbeid
    0.39
     âgées
    0.39
     usein
    0.38
    Activations Density 0.002%

    No Known Activations