© 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. 0-CLT-HP
    7. 41707
    Prev
    Next
    INDEX
    Explanations

    January

    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
    NavController
    -0.49
     that
    -0.44
    ified
    -0.44
     Thebes
    -0.43
     favoring
    -0.42
     sponsoring
    -0.42
    ,
    -0.41
    S
    -0.40
     What
    -0.40
     December
    -0.40
    POSITIVE LOGITS
    webElementXpaths
    0.71
    oneofs
    0.67
    oredCriteria
    0.63
     AppCompatTheme
    0.63
    OGND
    0.61
    ">//
    0.61
     Vikipedi
    0.60
    ècie
    0.60
    Хьажоргаш
    0.59
    følgelig
    0.57
    Activations Density 0.155%

    No Known Activations