© 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. 1-CLT-HP
    7. 15866
    Prev
    Next
    INDEX
    Explanations

    ma

    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
    ma
    -0.63
    MA
    -0.57
    Ma
    -0.56
    room
    -0.54
    ms
    -0.53
    ths
    -0.52
    mele
    -0.50
     Ma
    -0.50
    tw
    -0.50
    ism
    -0.49
    POSITIVE LOGITS
    ImageContext
    0.85
     AssemblyCulture
    0.66
     intptr
    0.65
     noDo
    0.64
    ]--;
    0.63
    AndEndTag
    0.61
    COUVER
    0.61
    astify
    0.59
     WQS
    0.59
     typelib
    0.58
    Activations Density 0.225%

    No Known Activations