© 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. 72362
    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
     Италијани
    -0.91
    rungsseite
    -0.91
    AndEndTag
    -0.88
    sizeCache
    -0.83
    يكب
    -0.80
    Personensuche
    -0.75
    WireFormatLite
    -0.75
    checkable
    -0.74
     Mother
    -0.74
    EndProject
    -0.73
    POSITIVE LOGITS
     hidrá
    0.41
    Wea
    0.40
     rodea
    0.39
    ssn
    0.38
    tonsoft
    0.36
    AnchorStyles
    0.35
     táctil
    0.33
     Anam
    0.33
     testigos
    0.33
    ENA
    0.32
    Activations Density 0.000%

    No Known Activations