© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38583
    Prev
    Next
    INDEX
    Explanations

    Internet Explorer

    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
     abuse
    -0.89
     abused
    -0.73
     abusing
    -0.72
     Abuse
    -0.70
     abusive
    -0.68
     Explorer
    -0.67
     abuses
    -0.65
     evil
    -0.63
     abuso
    -0.63
    abuse
    -0.63
    POSITIVE LOGITS
    MockBean
    0.57
    tonode
    0.55
    lwjgl
    0.49
     drama
    0.48
    OptionsMenu
    0.48
     joke
    0.47
     dinner
    0.46
    EDEFAULT
    0.46
    Autowired
    0.45
     StatefulWidget
    0.45
    Activations Density 1.531%

    No Known Activations