© 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. 20-CLT-HP
    7. 76496
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act-logits · 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
     Kün
    -0.61
     Efq
    -0.59
    bital
    -0.58
    cotch
    -0.58
     '\\;'
    -0.58
    pensione
    -0.58
    iforn
    -0.57
    piration
    -0.57
    IALES
    -0.57
    envolvimento
    -0.56
    POSITIVE LOGITS
     Release
    0.48
     âm
    0.45
     opérateur
    0.45
     Management
    0.43
    bolista
    0.42
     ferons
    0.41
    relsen
    0.41
    buttonBar
    0.40
     ENTRY
    0.40
     Module
    0.40
    Activations Density 0.001%

    No Known Activations