© 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. 1373
    Prev
    Next
    INDEX
    Explanations

    inspir

    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
    \)
    -0.54
    IFIED
    -0.50
    IFORNIA
    -0.49
    _'.$
    -0.49
     createState
    -0.48
    /")
    -0.48
    })_{
    -0.48
    IFORN
    -0.47
    '),
    -0.47
    Бахар
    -0.47
    POSITIVE LOGITS
    ItemLayout
    0.73
    quakes
    0.73
    featureID
    0.70
    BufferException
    0.69
    AxisAlignment
    0.68
    vician
    0.66
     Protestantism
    0.65
    TypeDef
    0.65
     sputnik
    0.62
     وتسجيلات
    0.62
    Activations Density 1.807%

    No Known Activations