© 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. 1-CLT-HP
    7. 10409
    Prev
    Next
    INDEX
    Explanations

    medical/scientific research

    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
    IConfiguration
    -0.50
    Geplaatst
    -0.49
    adget
    -0.46
    StackNavigator
    -0.45
    LookAnd
    -0.45
    ēr
    -0.44
    nex
    -0.44
    node
    -0.44
    bukkit
    -0.43
    ankt
    -0.42
    POSITIVE LOGITS
    \{\\
    0.80
    FieldBuilder
    0.67
     onCreateView
    0.65
    }$​
    0.62
    PerformLayout
    0.61
    Revenir
    0.56
    makeConstraints
    0.56
    ChildScrollView
    0.55
    ModelSerializer
    0.55
    Initializable
    0.54
    Activations Density 0.017%

    No Known Activations