© 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. 93425
    Prev
    Next
    INDEX
    Explanations

    config

    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
     IV
    -0.79
    Personendaten
    -0.65
    DockStyle
    -0.63
    Javadoc
    -0.57
    verifyException
    -0.57
     архивлан
    -0.55
    قایناق‌لار
    -0.54
    ViewStyle
    -0.54
     Vikipedi
    -0.54
    Glej
    -0.54
    POSITIVE LOGITS
     avoient
    0.71
     étoient
    0.65
     auroit
    0.62
     feroit
    0.60
     quæ
    0.57
     étoit
    0.56
     pouvoit
    0.56
    -------
    0.55
     enfans
    0.55
    DrawerToggle
    0.55
    Activations Density 0.177%

    No Known Activations