© 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. 5-CLT-HP
    7. 5548
    Prev
    Next
    INDEX
    Explanations

    of

    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
     nakalista
    -0.55
    WriteAttribute
    -0.50
    principalColumn
    -0.47
     ferons
    -0.47
     تانيه
    -0.45
    /><
    -0.39
     tacón
    -0.38
    MemoryWarning
    -0.38
     Onco
    -0.37
    TableId
    -0.37
    POSITIVE LOGITS
     mergeFrom
    0.63
     preparation
    0.63
     theſe
    0.62
     insurance
    0.59
    RTEE
    0.59
    CppMethod
    0.58
    chtenstein
    0.58
     inquest
    0.56
     coronation
    0.56
     eastern
    0.56
    Activations Density 0.002%

    No Known Activations