© 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. 92579
    Prev
    Next
    INDEX
    Explanations

    code and logs

    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
     autorytatywna
    -0.60
    Trama
    -0.54
    IonicModule
    -0.53
     INTERESAR
    -0.52
    :✨
    -0.52
     transacción
    -0.50
    geslacht
    -0.48
    GEBURTSDATUM
    -0.48
    fixing
    -0.46
    mediate
    -0.46
    POSITIVE LOGITS
    LookAnd
    0.63
     propOrder
    0.60
     toward
    0.54
    ValueGeneration
    0.53
    GetEnumerator
    0.51
     towards
    0.51
     tartalomajánló
    0.50
    endphp
    0.49
    withIdentifier
    0.48
     kaynağından
    0.48
    Activations Density 0.001%

    No Known Activations