© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43897
    Prev
    Next
    INDEX
    Explanations

    EMP

    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
    s
    -0.61
    parsedMessage
    -0.56
    eru
    -0.53
    openConnection
    -0.53
    ים
    -0.52
    ة
    -0.52
     esternos
    -0.51
    ValueStyle
    -0.50
    franc
    -0.50
    sre
    -0.49
    POSITIVE LOGITS
    ed
    0.81
    ette
    0.71
    GetAxis
    0.61
    age
    0.60
     nargin
    0.60
    ectomy
    0.59
     BoxFit
    0.59
    ever
    0.57
    postmedia
    0.57
    labus
    0.56
    Activations Density 0.298%

    No Known Activations