© 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. 1887
    Prev
    Next
    INDEX
    Explanations

    technical/abstract content

    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
    ScopeManager
    -0.71
    Cyfarwyddwr
    -0.71
    fromCharCode
    -0.68
     ligiloj
    -0.66
     שוליים
    -0.64
    estries
    -0.60
    eira
    -0.57
    gether
    -0.57
    GETHER
    -0.56
    .*")]
    -0.55
    POSITIVE LOGITS
    ]").
    0.67
    XmlAccessorType
    0.66
    []}
    0.58
    ][]
    0.57
    "}")
    0.56
     HRM
    0.55
    ValueStyle
    0.54
     fevere
    0.53
     Rasa
    0.52
     operacional
    0.52
    Activations Density 1.790%

    No Known Activations