© 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. 14740
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     CreateTagHelper
    -0.76
    SourceChecksum
    -0.54
     وتسجيلات
    -0.54
    ագրություններ
    -0.52
     Aner
    -0.50
     commod
    -0.50
     referenties
    -0.50
    RefNanny
    -0.49
    boutin
    -0.49
     שוליים
    -0.48
    POSITIVE LOGITS
    Hrsg
    0.62
    godic
    0.58
     dB
    0.54
    mogorov
    0.54
     windings
    0.54
    elemField
    0.53
    PSK
    0.53
    gbaar
    0.50
    prefixer
    0.49
    LSB
    0.49
    Activations Density 0.036%

    No Known Activations