© 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. 15387
    Prev
    Next
    INDEX
    Explanations

    estonia

    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
     choirs
    -0.92
     choir
    -0.89
     Choir
    -0.81
     pleaſure
    -0.79
     myſelf
    -0.78
     Reverso
    -0.76
     greateſt
    -0.75
     Theſe
    -0.75
     Monfieur
    -0.74
     fevere
    -0.73
    POSITIVE LOGITS
     الدولى
    0.52
    ErrUnexpectedEOF
    0.52
    :+:
    0.48
    room
    0.47
    antel
    0.41
     pav
    0.40
     pyplot
    0.40
    летия
    0.40
    axx
    0.40
    ন্ত
    0.40
    Activations Density 0.011%

    No Known Activations