© 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. 4-CLT-HP
    7. 590
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · 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
     Мексичка
    -0.75
    RegistryLite
    -0.70
    parsedMessage
    -0.69
    RetentionPolicy
    -0.67
    WebServlet
    -0.67
    Personendaten
    -0.65
    __);
    -0.64
     Significantly
    -0.63
     klokken
    -0.59
     Itself
    -0.59
    POSITIVE LOGITS
    pageY
    0.49
     ...]
    0.44
    ryn
    0.44
     estekak
    0.44
    JAKARTA
    0.43
    melten
    0.43
     Pao
    0.42
     Vereinigte
    0.42
    StatusBar
    0.41
     how
    0.41
    Activations Density 0.006%

    No Known Activations