© 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. 92530
    Prev
    Next
    INDEX
    Explanations

    the

    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
    yntaxException
    -0.56
     color
    -0.53
    SerializedSize
    -0.52
    styleable
    -0.50
    GraphicsUnit
    -0.50
    NewGuid
    -0.49
    getColumnIndex
    -0.48
    AYER
    -0.48
     linkovi
    -0.47
     way
    -0.47
    POSITIVE LOGITS
     CURIAM
    0.62
    addContainerGap
    0.59
    PRNewswire
    0.55
     ExecuteAsync
    0.54
    abestanden
    0.54
    WithIOException
    0.54
     насељу
    0.53
     MaterialApp
    0.52
    出版年
    0.51
    principalTable
    0.51
    Activations Density 0.005%

    No Known Activations