© 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. 5-CLT-HP
    7. 2783
    Prev
    Next
    INDEX
    Explanations

    1

    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
    WriteLiteral
    -0.57
    ::_('
    -0.54
    BeginInit
    -0.51
     $('#
    -0.50
     N
    -0.50
     ::
    -0.50
    ↵
    -0.50
     समीक्षक
    -0.50
     X
    -0.49
    IKAN
    -0.48
    POSITIVE LOGITS
     незавершена
    0.67
    Sucesor
    0.57
     défis
    0.57
     färg
    0.55
    ]")]
    0.53
     ModelExpression
    0.51
     gek
    0.50
     défi
    0.50
    Santis
    0.48
    spent
    0.48
    Activations Density 0.000%

    No Known Activations