© 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. 73467
    Prev
    Next
    INDEX
    Explanations

    Non-English 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
    OIR
    -0.42
    initState
    -0.42
     Facility
    -0.40
     andato
    -0.40
    ol
    -0.39
    ňa
    -0.39
     localStorage
    -0.38
     πό
    -0.38
     mui
    -0.38
    PCell
    -0.37
    POSITIVE LOGITS
    Datuak
    0.77
     صوتيه
    0.75
     cafes
    0.74
     '{@
    0.71
     restaurants
    0.70
    XmlAccessorType
    0.69
    restaurants
    0.69
     EconPapers
    0.68
     autorytatywna
    0.66
     cafeter
    0.64
    Activations Density 0.001%

    No Known Activations