© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41471
    Prev
    Next
    INDEX
    Explanations

    computers and servers

    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
    ^(@)
    -1.04
    setupUi
    -0.98
     tartalomajánló
    -0.97
     myſelf
    -0.96
    CppMethod
    -0.94
     itſelf
    -0.94
     auffi
    -0.94
    parsedMessage
    -0.92
     Efq
    -0.91
    >\<^
    -0.89
    POSITIVE LOGITS
    In
    0.69
     
    0.63
    ↵
    0.61
    For
    0.61
    As
    0.61
    To
    0.60
    S
    0.59
    L
    0.59
    One
    0.57
     In
    0.57
    Activations Density 0.134%

    No Known Activations