© 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. 1-CLT-HP
    7. 13342
    Prev
    Next
    INDEX
    Explanations

    neuroscience

    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
     referenties
    -0.85
     AttributeSet
    -0.81
    Билгалдахарш
    -0.75
    Зноскі
    -0.73
    脚注の使い方
    -0.73
     giuri
    -0.73
    abstractmethod
    -0.72
     متعلقه
    -0.71
    netje
    -0.71
     StatefulWidget
    -0.71
    POSITIVE LOGITS
    poto
    0.53
     Send
    0.39
    /−
    0.38
    Enviado
    0.37
    }}}
    0.35
     kernel
    0.35
     components
    0.35
     mut
    0.34
    |]
    0.34
    `}
    0.33
    Activations Density 0.100%

    No Known Activations