© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97857
    Prev
    Next
    INDEX
    Explanations

    forklifts and equipment

    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
     répon
    -0.56
    gesehen
    -0.55
    dengar
    -0.51
     ModelExpression
    -0.49
     AspNetCore
    -0.47
     prends
    -0.47
     fous
    -0.47
    ames
    -0.47
    mea
    -0.46
    程
    -0.46
    POSITIVE LOGITS
    truck
    0.78
    lifts
    0.74
    trucks
    0.69
    Personendaten
    0.67
     truck
    0.66
    lif
    0.65
     Мексичка
    0.65
    lift
    0.61
    GraphicsUnit
    0.61
    jacks
    0.61
    Activations Density 0.002%

    No Known Activations